[{"object_id":"https://biocomputeobject.org/GLY_000001/2.0.3","contents":{"object_id":"https://biocomputeobject.org/GLY_000001/2.0.3","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2022-09-26T08:44:32.945603","version":"2.0.3"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1bbf8878ac72b2c9aebb2bb675f1738a5315c73d86079d8815d842e4a904e735","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.stat.csv","filename":"human_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:16:27.427000Z","access_count":40},{"object_id":"https://biocomputeobject.org/GLY_000001/2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000001/2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2022-09-26T08:44:32.945603","version":"2.1.1"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1bbf8878ac72b2c9aebb2bb675f1738a5315c73d86079d8815d842e4a904e735","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.stat.csv","filename":"human_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:18:07.256000Z","access_count":37},{"object_id":"https://biocomputeobject.org/GLY_000001/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000001/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2024-06-03T20:25:49.285Z","version":"v-0.0.0"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human Proteome Masterlist dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"3f81a26433cdab30463f31bffcb3eeefcaabacf78439f0be78852dc62aec7daa","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_masterlist.stat.csv","filename":"human_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":292,"last_update":"2024-06-03T20:25:49.285361Z","access_count":17},{"object_id":"https://biocomputeobject.org/GLY_000001/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000001/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2022-09-26T08:44:32.945603","version":"v-2.0.2"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1bbf8878ac72b2c9aebb2bb675f1738a5315c73d86079d8815d842e4a904e735","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.stat.csv","filename":"human_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.231000Z","access_count":56},{"object_id":"https://biocomputeobject.org/GLY_000001/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000001/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2022-09-26T08:44:32.945603","version":"v-2.1.1"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f504cfea3e6f26ef0eff3919869f78c4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.stat.csv","filename":"human_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:51:10.281000Z","access_count":42},{"object_id":"https://biocomputeobject.org/GLY_000002/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000002/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.868557","modified":"2024-06-03T20:26:24.051Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all human canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human Protein Canonical (UniProtKB) Sequences dataset contains Homo sapiens [taxid:9606] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"ffe55c42f58c4e9d92b24613ac1d92b2bdc09b4189c92f2253df49bac27979c2","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_canonicalsequences.stat.csv","filename":"human_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":247,"last_update":"2024-06-03T20:26:24.051863Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000002/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000002/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.868557","modified":"2022-09-26T08:44:32.944414","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all human canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Canonical (UniProtKB) Sequences dataset contains human [taxid:9606] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"6a1e24ada535192808e37a81aa1a88c7b703a9fdfc5a309bb25a23f996e08d3c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_canonicalsequences.stat.csv","filename":"human_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.220000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000002/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000002/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.868557","modified":"2022-09-26T08:44:32.944414","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all human canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Canonical (UniProtKB) Sequences dataset contains human [taxid:9606] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"231846dc9ac03559a4efee36b2d29b72","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_canonicalsequences.stat.csv","filename":"human_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:50:45.650000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000003/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000003/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.869598","modified":"2024-05-17T11:23:49.279Z","version":"v-0.0.0"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human EBI-UniProtKB NT file contains proteome data for Homo sapiens [taxid:9606] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"dd1b2dc28d79215909886d11d6ce76294ac1df55107406d434be622da6d8e2a9","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_ntdata.stat.csv","filename":"human_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":270,"last_update":"2024-05-17T11:23:49.279925Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000003/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000003/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.869598","modified":"2022-09-26T08:44:32.943185","version":"v-2.0.2"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human EBI-UniProtKB NT file contains proteome data for human [taxid:9606] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"dd159dfad184a4724f9adaa516040be80445b36d5f64b5e1aef92a4e776a183d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_ntdata.stat.csv","filename":"human_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.146000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000003/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000003/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.869598","modified":"2022-09-26T08:44:32.943185","version":"v-2.1.1"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human EBI-UniProtKB NT file contains proteome data for human [taxid:9606] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e307aaf09ea6e71d10256f7595980c28","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_ntdata.stat.csv","filename":"human_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:37.978000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000004/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000004/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f693fbf3988c622af336d3bd33fbcee26cc9fecb45290fe525f3f6fea8918eae","provenance_domain":{"name":"Human Glycosyltransferases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.870634","modified":"2024-12-10T16:52:20.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosyltransferases dataset contains list of Homo sapiens [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the human proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Homo sapiens (Human) [9606]\". To retrieve the list of all human glycosyltransferases, the full list of human proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycosyltransferase.stat.csv","filename":"human_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":2395,"last_update":"2024-12-10T16:52:20.479501Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000004/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000004/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosyltransferases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.870634","modified":"2022-09-26T08:44:32.941831","version":"v-2.0.2"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosyltransferases dataset contains list of human [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the human proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Homo sapiens (Human) [9606]\". To retrieve the list of all human glycosyltransferases, the full list of human proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"etag":"578ad9305fec3f17278def657be9b4669040378638708162a3f7e5436a83c0a9","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_glycosyltransferase.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycosyltransferase.stat.csv","filename":"human_protein_glycosyltransferase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.119000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000004/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000004/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosyltransferases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.870634","modified":"2022-09-26T08:44:32.941831","version":"v-2.1.1"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosyltransferases dataset contains list of human [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the human proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Homo sapiens (Human) [9606]\". To retrieve the list of all human glycosyltransferases, the full list of human proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"etag":"6d0a417eafd52a13da7124e001aa6efa","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_glycosyltransferase.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycosyltransferase.stat.csv","filename":"human_protein_glycosyltransferase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:38.156000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000007/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000007/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2024-05-17T11:23:49.370Z","version":"v-0.0.0"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Proteome Masterlist dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"3e7e2085e483bce21cac743d581a048caa1d5bcfac1dfc932eb2dd2f948a4102","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_masterlist.stat.csv","filename":"mouse_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":366,"last_update":"2024-05-17T11:23:49.370145Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000007/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000007/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2022-09-26T08:44:32.947966","version":"v-2.0.2"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Proteome Masterlist dataset contains mouse [taxid:10090] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"06a4f3aac2879db86b4c4795bc8540c8f5be9a5afafbe18a0466fdd34bfad4df","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.stat.csv","filename":"mouse_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.414000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000007/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000007/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.867420","modified":"2022-09-26T08:44:32.947966","version":"v-2.1.1"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Proteome Masterlist dataset contains mouse [taxid:10090] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"4c6061e01667328e68e8a912f4392df0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.stat.csv","filename":"mouse_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:38.341000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000012/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000012/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.878935","modified":"2024-05-17T11:23:49.409Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence","fasta","canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Canonical (UniProtKB) Sequences dataset contains Mus musculus [taxid:10090] protein canonical fasta sequences from the UniProtKB database. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e14f9a3b02050206df33047177277573b124b68f6239aebd218bef17213a333e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_canonicalsequences.stat.csv","filename":"mouse_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":321,"last_update":"2024-05-17T11:23:49.409111Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000012/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000012/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.878935","modified":"2022-09-26T08:44:32.940877","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence","fasta","canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Canonical (UniProtKB) Sequences dataset contains mouse [taxid:10090] protein canonical fasta sequences from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"171298c5621a5cc47fa250373556da5985f66a721a7c6b6bea2e6c5b9bf742f1","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_canonicalsequences.stat.csv","filename":"mouse_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.613000Z","access_count":37},{"object_id":"https://biocomputeobject.org/GLY_000012/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000012/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.878935","modified":"2022-09-26T08:44:32.940877","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence","fasta","canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Canonical (UniProtKB) Sequences dataset contains mouse [taxid:10090] protein canonical fasta sequences from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8198ecf5961042988030ef9d5b7a115e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_canonicalsequences.stat.csv","filename":"mouse_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:38.512000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000013/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000013/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.879959","modified":"2024-05-17T11:23:49.449Z","version":"v-0.0.0"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse EBI-UniProtKB NT file contains proteome data for Mus musculus [taxid:10090] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d5ed6c5d6bdcffe0c407766bfa7ce39ec250339ba18efd5180563defe2bc97b5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_ntdata.stat.csv","filename":"mouse_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":271,"last_update":"2024-05-17T11:23:49.449964Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000013/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000013/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.879959","modified":"2022-09-26T08:44:32.939883","version":"v-2.0.2"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse EBI-UniProtKB NT file contains proteome data for mouse [taxid:10090] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e2f97e5c144fa08c5d52c83bf71b4bbe75f27a580b3e2f46802d3bd1ae7d6fe5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_ntdata.stat.csv","filename":"mouse_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.114000Z","access_count":37},{"object_id":"https://biocomputeobject.org/GLY_000013/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000013/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.879959","modified":"2022-09-26T08:44:32.939883","version":"v-2.1.1"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse EBI-UniProtKB NT file contains proteome data for mouse [taxid:10090] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0600acf2abe14b16eecc53db3c143611","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_ntdata.stat.csv","filename":"mouse_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:38.689000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000021/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000021/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.888176","modified":"2024-05-17T11:23:49.489Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Information (NCBI RefSeq) dataset contains Homo sapiens [taxid:9606] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"51fba1392877ac70fefd8ed9b9a48dbcad933572f5467639ccdf75f2eb7ebb31","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_info_refseq.stat.csv","filename":"human_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":287,"last_update":"2024-05-17T11:23:49.489828Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000021/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000021/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-01-23T17:21:05.888176","modified":"2022-09-26T08:44:32.946781","version":"v-2.0.2"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Information (NCBI RefSeq) dataset contains human [taxid:9606] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"36884c298822241f02f7c16caf519dc2c442314551434a27763fa86702038ef2","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_9606.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_9606.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_info_refseq.stat.csv","filename":"human_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.806000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000021/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000021/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.888176","modified":"2022-09-26T08:44:32.946781","version":"v-2.1.1"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Information (NCBI RefSeq) dataset contains human [taxid:9606] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"d6f8e24990ba30e7a90b0292d7a66878","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_9606.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_9606.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_info_refseq.stat.csv","filename":"human_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:38.861000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000022/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000022/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.888176","modified":"2024-05-17T11:23:49.528Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein information","protein length","protein summary","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Information (NCBI RefSeq) dataset contains Mus musculus [taxid:10090] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"587e97c1a65ace877683a49a418bfc4f43b766eddc263626b1ae681cd519072c","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_info_refseq.csv","filename":"mouse_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_info_refseq.stat.csv","filename":"mouse_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":288,"last_update":"2024-05-17T11:23:49.528823Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000022/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000022/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-01-23T17:21:05.888176","modified":"2022-09-26T08:48:18.844146","version":"v-2.0.2"},"description_domain":{"keywords":["protein information","protein length","protein summary","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_refseq_protein_info.csv","filename":"mouse_protein_refseq_protein_info.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Information (NCBI RefSeq) dataset contains mouse [taxid:10090] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"24c54c3e8d25c38e2dfb93c1dca35c9ca96bc5b2d392d2202db64028f313d907","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10090.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_10090.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_info_refseq.csv","filename":"mouse_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_info_refseq.stat.csv","filename":"mouse_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.055000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000022/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000022/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.888176","modified":"2022-09-26T08:48:18.844146","version":"v-2.1.1"},"description_domain":{"keywords":["protein information","protein length","protein summary","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_refseq_protein_info.csv","filename":"mouse_protein_refseq_protein_info.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Information (NCBI RefSeq) dataset contains mouse [taxid:10090] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"63d33bfa594f657345a997f81509a6a3","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10090.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_10090.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_refseq.csv","filename":"mouse_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_refseq.stat.csv","filename":"mouse_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:39.045000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000024/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000024/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"83b464f1f6bb3acd80966aafdc9bef4ca0713ce4be7ea229e82b9e5b3bad6d8b","provenance_domain":{"name":"Human Cancer Mutation","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.891293","modified":"2026-07-08T10:52:25.123Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Human Cancer Mutation dataset contains Homo sapiens [taxid:9606] mutation data from the BioMuta database (https://hive.biochemistry.gwu.edu/biomuta). The BioMuta pipeline documentation can be found on the HIVE Lab Wiki: https://hivelab.biochemistry.gwu.edu/wiki/BioMuta_pipeline_README.","The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.","BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.","The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset, please provide proper attribution to BioMuta and GlyGen.","Note that the mutations in GlyGen are annotated based on passing of one or more filter criteria.","Filter criterion 1 - Positive Patients Frequency Ratio ≥ 1.0%","Filter criterion 2 - Presence of mutation in ≥ 3 cancer types","Filter criterion 3 - Positive Patients count ≥ 10 patients","Filter criterion 4 - Mutation reported and annotated in number of databases","Filter criterion 5 - Mutation mined from literature using literature mining tools (human_protein_mutation_literature.csv)","Filter criterion 6 -  At least one glyco-relevant mutation effect i.e. N-glycosylation sequon loss, N-glycosylation sequon gain or O-glycosylation site loss.","If there is also a germline mutation reported in dbSNP, the rsid is also shown","Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias"}],"keywords":["single-nucleotide variations (nsSNVs)","cancer mutations","BioMuta","disease"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_cancer.stat.csv","filename":"human_protein_mutation_cancer.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1940,"last_update":"2026-07-08T10:52:25.123352Z","access_count":13},{"object_id":"https://biocomputeobject.org/GLY_000024/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000024/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Cancer Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-01-23T17:21:05.891293","modified":"2022-09-26T08:48:18.834228","version":"v-2.0.2"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","cancer mutations","BioMuta","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/mutid-map.final.csv","filename":"mutid-map.final.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_cancer_mutation_somatic.csv","filename":"human_cancer_mutation_somatic.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}],"prerequisite":[],"description":"The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Cancer Mutation dataset contains human [taxid:9606] mutation data from BioMuta database (https://hive.biochemistry.gwu.edu/biomuta).","The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.","BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.","The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset please provide proper attribution to BioMuta and GlyGen. ","Note the mutation shown in GlyGen are annotated based on passing of one or more filter criterias.","Filter criteria 1 - Positive Patient's Frequency Ratio ≥ 1.0%","Filter criteria 2 - Presence of mutation in number of cancer types ≥ 3 cancer types","Filter criteria 3 - Positive Patient's count ≥ 10 patients","Filter criteria 4 - Mutation reported and annotated in number of databases","Filter criteria 5 - Mutation minned from the literature using literaure mining tools (human_protein_mutation_literature.csv)","If there is also a germline mutation reported in dbSNP, the rsid is also shown","These filter criteria annotations are shown on the front end under the column Annotation Name","Also if the same mutation in the same cancer type on a given protein is reported in ICGC and TCGA then mutations from TCGA are only shown.","When mutations from TCGA are not available but are present in ICGC for the same protein and cancer type, ICGC mutations are shown in GlyGen","Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim.","On the GlyGen interface, in Mutations section the mutations that have passed highest number of filter criteria are displayed first irrespective of their amio acid positions. For eg. the mutation entry that has passed 5 filter criteria will be shown first."],"etag":"e0057283a251b5aa36b08f51f59273c120b4cd1d3c1ddafc8a6c4d7cf648c09b","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_literature.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}},{"uri":{"filename":"mutid-map.final.csv","uri":"https:/data.glygen.org/ln2downloads/biomuta/v-3.0/mutid-map.final.csv"}},{"uri":{"filename":"dbSNP-homo-sapiens.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/dbSNP-homo-sapiens.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer.stat.csv","filename":"human_protein_mutation_cancer.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.355000Z","access_count":37},{"object_id":"https://biocomputeobject.org/GLY_000024/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000024/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Cancer Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.891293","modified":"2022-09-26T08:48:18.834228","version":"v-2.1.1"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","cancer mutations","BioMuta","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/mutid-map.final.csv","filename":"mutid-map.final.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_cancer_mutation_somatic.csv","filename":"human_cancer_mutation_somatic.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}],"prerequisite":[],"description":"The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Cancer Mutation dataset contains human [taxid:9606] mutation data from BioMuta database (https://hive.biochemistry.gwu.edu/biomuta).","The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.","BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.","The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset please provide proper attribution to BioMuta and GlyGen. ","Note the mutation shown in GlyGen are annotated based on passing of one or more filter criterias.","Filter criteria 1 - Positive Patient's Frequency Ratio ≥ 1.0%","Filter criteria 2 - Presence of mutation in number of cancer types ≥ 3 cancer types","Filter criteria 3 - Positive Patient's count ≥ 10 patients","Filter criteria 4 - Mutation reported and annotated in number of databases","Filter criteria 5 - Mutation minned from the literature using literaure mining tools (human_protein_mutation_literature.csv)","If there is also a germline mutation reported in dbSNP, the rsid is also shown","These filter criteria annotations are shown on the front end under the column Annotation Name","Also if the same mutation in the same cancer type on a given protein is reported in ICGC and TCGA then mutations from TCGA are only shown.","When mutations from TCGA are not available but are present in ICGC for the same protein and cancer type, ICGC mutations are shown in GlyGen","Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim.","On the GlyGen interface, in Mutations section the mutations that have passed highest number of filter criteria are displayed first irrespective of their amio acid positions. For eg. the mutation entry that has passed 5 filter criteria will be shown first."],"etag":"df4625868abe051fc1ac3fdcb3e46ebc","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_literature.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}},{"uri":{"filename":"biomuta.csv","uri":"/data/shared/glyds/downloads/biomuta/v-5.0/biomuta.csv"}},{"uri":{"filename":"clinical_information.csv","uri":"/data/shared/glyds/downloads/biomuta/v-5.0/clinical_information.csv"}},{"uri":{"filename":"dbSNP-homo-sapiens.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/dbSNP-homo-sapiens.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.stat.csv","filename":"human_protein_mutation_cancer.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:39.245000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000025/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000025/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"150e80e2c088d7168bdd5ba70c1ea247473a57f3822c800d084a40471afaf29a","provenance_domain":{"name":"Human Glycohydrolases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.892318","modified":"2024-12-10T16:54:17.429Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycohydrolases dataset contains a list of Homo sapiens [taxid:9606] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycohydrolase.stat.csv","filename":"human_protein_glycohydrolase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2024-12-10T16:54:17.429733Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000025/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000025/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycohydrolases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.892318","modified":"2022-09-26T08:48:18.827093","version":"v-2.0.2"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycohydrolases dataset contains a list of human [taxid:9606] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"cc5dc4bffb6d6fe7348797de2bd99fdea3703532e357e721eb09ed6ad6a00ec9","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_glycohydrolase.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycohydrolase.stat.csv","filename":"human_protein_glycohydrolase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.028000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000025/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000025/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycohydrolases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.892318","modified":"2022-09-26T08:48:18.827093","version":"v-2.1.1"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycohydrolases dataset contains a list of human [taxid:9606] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"f9241aefe29d6461970c8935d2ac15b5","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_glycohydrolase.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycohydrolase.stat.csv","filename":"human_protein_glycohydrolase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:39.449000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000026/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000026/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c0ca9479039d742c9228213d6d24cb8ecf44dc67bb4de0c84f61e5b251efa4ac","provenance_domain":{"name":"Mouse Glycohydrolases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.893381","modified":"2024-12-10T17:42:02.338Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycohydrolases dataset contains a list of Mus musculus [taxid:10090] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycohydrolase.stat.csv","filename":"mouse_protein_glycohydrolase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2024-12-10T17:42:02.338100Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000026/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000026/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycohydrolases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.893381","modified":"2022-09-26T08:48:18.871781","version":"v-2.0.2"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycohydrolases dataset contains a list of mouse [taxid:10090] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"dba2ca859b8495a75ea1db6cce809eef318b69ddf395bf5f9c2c4d424f60afcd","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/mouse_protein_glycohydrolase.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycohydrolase.stat.csv","filename":"mouse_protein_glycohydrolase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.493000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000026/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000026/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycohydrolases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.893381","modified":"2022-09-26T08:48:18.871781","version":"v-2.1.1"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycohydrolases dataset contains a list of mouse [taxid:10090] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"68c08126a88b950ed7d3351390a8485c","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/mouse_protein_glycohydrolase.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycohydrolase.stat.csv","filename":"mouse_protein_glycohydrolase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:39.628000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000028/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000028/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fd9f554c61ef864340611d31ce2cd4d72ac00dd8bec2f5562e8d1a792d830385","provenance_domain":{"name":"Gene Expression (Normal)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.895453","modified":"2024-12-10T16:54:49.405Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Gene Expression (Normal) dataset contains the normal expression information of Homo sapiens [taxid:9606] genes from BioXpress database. The GlyGen Interface shows the normal gene expression information for select UBERON ids only which are mapped to corresponding DOIDs and have gene expression in cancer information for those DOID. For more gene expression information of other UBERON IDs (tissues) for a given gene, please refer to BioXpress - https://hive.biochemistry.gwu.edu/bioxpress. BioXpress is a gene/miRNA expression and disease association database with expression levels mapped to genes or miRNAs. The current version of BioXpress contains only genes associated with cancer. If you are using this dataset please give proper attribution to GlyGen and BioXpress"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the expression information and maps the UniProtKB accession/gene symbol to UniProtKB canonical expression"}],"keywords":["normal gene expression","BioXpress","UBERON","tissue","Bgee"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_expression_normal.stat.csv","filename":"human_protein_expression_normal.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Normal Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":935,"last_update":"2024-12-10T16:54:49.405105Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000028/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000028/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Normal Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Gene Expression (Normal)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-01-23T17:21:05.895453","modified":"2022-09-26T08:48:18.830871","version":"v-2.0.2"},"description_domain":{"keywords":["normal gene expression","BioXpress","UBERON","tissue","Bgee"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}],"prerequisite":[],"description":"The script extracts the expression information and maps the UniProtKB accession/gene symbol to UniProtKB canonical expression"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Gene Expression (Normal) dataset contains the normal expression information of human [taxid:9606] genes from BioXpress database. The GlyGen Interface shows the normal gene expression information for select UBERON ids only which are mapped to corresponding DOIDs and have gene expression in cancer information for those DOID. For more gene expression information of other UBERON IDs (tissues) for a given gene, please refer to BioXpress - https://hive.biochemistry.gwu.edu/bioxpress. BioXpress is a gene/miRNA expression and disease association database with expression levels mapped to genes or miRNAs. The current version of BioXpress contains only genes associated with cancer. If you are using this dataset please give proper attribution to GlyGen and BioXpress"],"etag":"25121290adfc1ab7b171ffaa1957c44c95fc857e5f96cd178a71fdfe199a3b87","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"doid2uberonid_mapping_v5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/doid2uberonid_mapping_v5.csv"}},{"uri":{"filename":"human_normal_expression_custom_filtered.csv","uri":"https:/data.glygen.org/ln2downloads/bioxpress/2021_08/human_normal_expression_custom_filtered.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_expression_normal.stat.csv","filename":"human_protein_expression_normal.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.854000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000028/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000028/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Normal Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Gene Expression (Normal)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.895453","modified":"2022-09-26T08:48:18.830871","version":"v-2.1.1"},"description_domain":{"keywords":["normal gene expression","BioXpress","UBERON","tissue","Bgee"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}],"prerequisite":[],"description":"The script extracts the expression information and maps the UniProtKB accession/gene symbol to UniProtKB canonical expression"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Gene Expression (Normal) dataset contains the normal expression information of human [taxid:9606] genes from BioXpress database. The GlyGen Interface shows the normal gene expression information for select UBERON ids only which are mapped to corresponding DOIDs and have gene expression in cancer information for those DOID. For more gene expression information of other UBERON IDs (tissues) for a given gene, please refer to BioXpress - https://hive.biochemistry.gwu.edu/bioxpress. BioXpress is a gene/miRNA expression and disease association database with expression levels mapped to genes or miRNAs. The current version of BioXpress contains only genes associated with cancer. If you are using this dataset please give proper attribution to GlyGen and BioXpress"],"etag":"4dac5c591db03a96bfe0fd00bfd9b294","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"doid2uberonid_mapping_v5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/doid2uberonid_mapping_v5.csv"}},{"uri":{"filename":"human_normal_expression_custom_filtered.csv","uri":"/data/shared/glyds/downloads/bioxpress/2021_08/human_normal_expression_custom_filtered.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_expression_normal.stat.csv","filename":"human_protein_expression_normal.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:39.889000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000029/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000029/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Gene Expression (Cancer)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.896478","modified":"2024-05-17T11:23:49.733Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene expression (cancer)","Disease Ontology","differential expression","BioXpress"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the expression information and maps the UniProtKB accession/ gene name to UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Gene Expression (Cancer) dataset contains the gene expression information in cancers from BioXpress database. The GlyGen interface shows the gene expression (cancer) information for select cancer types/DOIDs. For more cancer types/DOIDs please refer - https://hive.biochemistry.gwu.edu/bioxpress. If you use this dataset please give proper attribution to BioXpress and GlyGen."],"etag":"2631fd4ad9d8c07e8ad163c5d900fa14a982f0b5da33358814625ee5b4e1fbbd","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_expression_disease.csv","filename":"human_protein_expression_disease.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_expression_disease.stat.csv","filename":"human_protein_expression_disease.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":376,"last_update":"2024-05-17T11:23:49.733293Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000029/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000029/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Gene Expression (Cancer)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-01-23T17:21:05.896478","modified":"2022-09-26T08:48:18.829918","version":"v-2.0.2"},"description_domain":{"keywords":["gene expression (cancer)","Disease Ontology","differential expression","BioXpress"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_protein_expression_cancer.csv","filename":"human_protein_expression_normal.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_protein_expression_cancer.csv","filename":"human_protein_expression_cancer.csv"}],"prerequisite":[],"description":"The script extracts the expression information and maps the UniProtKB accession/ gene name to UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Gene Expression (Cancer) dataset contains the gene expression information in cancers from BioXpress database. The GlyGen interface shows the gene expression (cancer) information for select cancer types/DOIDs. For more cancer types/DOIDs please refer - https://hive.biochemistry.gwu.edu/bioxpress. If you use this dataset please give proper attribution to BioXpress and GlyGen."],"etag":"12b06c3f358c727f243a8f98898f2831550fc4fe4fccf58d1dbc9c81312b7ef0","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_cancer_mRNA_expression_per_tissue_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/bioxpress/2021_08/human_cancer_mRNA_expression_per_tissue_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_expression_disease.csv","filename":"human_protein_expression_disease.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_expression_disease.stat.csv","filename":"human_protein_expression_disease.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.741000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000029/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000029/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Gene Expression (Cancer)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.896478","modified":"2022-09-26T08:48:18.829918","version":"v-2.1.1"},"description_domain":{"keywords":["gene expression (cancer)","Disease Ontology","differential expression","BioXpress"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_protein_expression_cancer.csv","filename":"human_protein_expression_normal.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_protein_expression_cancer.csv","filename":"human_protein_expression_cancer.csv"}],"prerequisite":[],"description":"The script extracts the expression information and maps the UniProtKB accession/ gene name to UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Gene Expression (Cancer) dataset contains the gene expression information in cancers from BioXpress database. The GlyGen interface shows the gene expression (cancer) information for select cancer types/DOIDs. For more cancer types/DOIDs please refer - https://hive.biochemistry.gwu.edu/bioxpress. If you use this dataset please give proper attribution to BioXpress and GlyGen."],"etag":"a3e64b8b22c6dd818d056c5b89094816","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_cancer_mRNA_expression_per_tissue_glygen.csv","uri":"/data/shared/glyds/downloads/bioxpress/2021_08/human_cancer_mRNA_expression_per_tissue_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_expression_disease.csv","filename":"human_protein_expression_disease.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_expression_disease.stat.csv","filename":"human_protein_expression_disease.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:40.078000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000030/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000030/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0a6f240804884d29f6ede8a7dc5577b4b1d8734f8cd833f9c5853d07a5822acf","provenance_domain":{"name":"Mouse Glycosyltransferases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.897519","modified":"2024-12-10T17:37:44.783Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosyltransferases dataset contains a list of Mus musculus [taxid:10090] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["GT","gycosyltransferase","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycosyltransferase.stat.csv","filename":"mouse_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2024-12-10T17:37:44.783253Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000030/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000030/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosyltransferases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.897519","modified":"2022-09-26T08:48:18.868938","version":"v-2.0.2"},"description_domain":{"keywords":["GT","gycosyltransferase","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosyltransferases dataset contains a list of mouse [taxid:10090] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"cb579e1e2957a7cff1c2b7029409e263f7db1df6538ff7327e7013f9de833c0c","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/mouse_protein_glycosyltransferase.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycosyltransferase.stat.csv","filename":"mouse_protein_glycosyltransferase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:53.971000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000030/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000030/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosyltransferases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.897519","modified":"2022-09-26T08:48:18.868938","version":"v-2.1.1"},"description_domain":{"keywords":["GT","gycosyltransferase","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosyltransferases dataset contains a list of mouse [taxid:10090] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"ce5d1d1623424aa36a392e712b55f0f0","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/mouse_protein_glycosyltransferase.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycosyltransferase.stat.csv","filename":"mouse_protein_glycosyltransferase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:40.265000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000031/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000031/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.898547","modified":"2024-05-17T11:23:49.816Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Homo sapiens [taxid:9606] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8471cd508dde19554b946f9441dfd21b2d9ff1ef1859d9f5c2c90336f9ab03c4","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_altnames.stat.csv","filename":"human_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":222,"last_update":"2024-05-17T11:23:49.816298Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000031/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000031/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.898547","modified":"2022-09-26T08:48:18.864185","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for human [taxid:9606] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"3986f5fbb4be065c4807e312fcb9db1e7b4ccc50f3fc1f53f62112bf3ea48f3b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_altnames.stat.csv","filename":"human_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.459000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000031/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000031/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.898547","modified":"2022-09-26T08:48:18.864185","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for human [taxid:9606] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1556bd75f777e948cbd34047f36b01c9","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_altnames.stat.csv","filename":"human_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:40.466000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000032/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000032/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.899575","modified":"2024-05-17T11:23:49.856Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Mus musculus [taxid:10090] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"a77566201c17261e20f4c5e24f1e681f5b6f3499e10525ea38750fffd031b795","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_altnames.stat.csv","filename":"mouse_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":223,"last_update":"2024-05-17T11:23:49.856503Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000032/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000032/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.899575","modified":"2022-09-26T08:48:18.835460","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for mouse [taxid:10090] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"c63a046e8dce42be7c8558c60f1389ea1700535106409a99087436df814631fc","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_altnames.stat.csv","filename":"mouse_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.936000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000032/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000032/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.899575","modified":"2022-09-26T08:48:18.835460","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for mouse [taxid:10090] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"2c904dcc6ca9958903e93093a3377cbb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_altnames.stat.csv","filename":"mouse_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:40.661000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000033/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000033/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.900608","modified":"2024-05-17T11:23:49.897Z","version":"v-0.0.0"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Information dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0ae0dae96cce4d99db88af76009ab020be3e47e0666c579dac40ba233a350679","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_info_uniprotkb.csv","filename":"human_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_info_uniprotkb.stat.csv","filename":"human_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":280,"last_update":"2024-05-17T11:23:49.897682Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000033/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000033/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.900608","modified":"2022-09-26T08:48:18.826045","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_info_uniprotkb.csv","filename":"human_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Information dataset contains human [taxid:9606] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"41c9b81f6a4e45fc298c525fba5d1e643d9147c13881882d9701176b4f5cab1a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_info_uniprotkb.csv","filename":"human_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_info_uniprotkb.stat.csv","filename":"human_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.918000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000033/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000033/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.900608","modified":"2022-09-26T08:48:18.826045","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_info_uniprotkb.csv","filename":"human_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Information dataset contains human [taxid:9606] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8f7cea92002399d657024c4a6b507d6d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_info_uniprotkb.csv","filename":"human_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_info_uniprotkb.stat.csv","filename":"human_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:40.930000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000034/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000034/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.901631","modified":"2024-06-03T20:27:04.962Z","version":"v-0.0.0"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Protein Information dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"db2ca0d6f2c5ca7eb54bd5907142b4c08d95c93327ed5feab4151baf35d6cc03","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_info_uniprotkb.csv","filename":"mouse_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_info_uniprotkb.stat.csv","filename":"mouse_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":282,"last_update":"2024-06-03T20:27:04.962410Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000034/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000034/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.901631","modified":"2022-09-26T08:48:18.846390","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_info_uniprotkb.csv","filename":"mouse_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Information dataset contains mouse [taxid:10090] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e03ba08c7e1c77c7968e2f6a2d3c0c67e9b062e307090206663281da68f212de","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_info_uniprotkb.csv","filename":"mouse_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_info_uniprotkb.stat.csv","filename":"mouse_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.275000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000034/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000034/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.901631","modified":"2022-09-26T08:48:18.846390","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_info_uniprotkb.csv","filename":"mouse_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Information dataset contains mouse [taxid:10090] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"5ce0fadd9e7fa33ddb132d91131126af","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_uniprotkb.csv","filename":"mouse_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_uniprotkb.stat.csv","filename":"mouse_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:41.117000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000035/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000035/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.902655","modified":"2024-05-17T11:23:49.977Z","version":"v-0.0.0"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human Protein Citations dataset contains publication information for Homo sapiens [taxid:9606] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"7cb5efb4db39348a51a7b83ce672fc2c5db62c684d0d8a7f91db644c5aa895ec","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_uniprotkb.stat.csv","filename":"human_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":416,"last_update":"2024-05-17T11:23:49.977705Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000035/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000035/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.902655","modified":"2022-09-26T08:48:18.842206","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_protein_blacklisted_pmids_uniprotkb.csv","filename":"human_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Citations dataset contains publication information for human [taxid:9606] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/human_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8d3b503cea60b7a7fdfa1f5e88edb3574a9075a0c069947e5846dc7ed557d06a","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_uniprotkb.stat.csv","filename":"human_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.449000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000035/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000035/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.902655","modified":"2022-09-26T08:48:18.842206","version":"v-2.1.1"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/human_protein_blacklisted_pmids_uniprotkb.csv","filename":"human_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Citations dataset contains publication information for human [taxid:9606] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/human_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"c8450a61ca6123361fe80c4f6533c3fa","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_uniprotkb.stat.csv","filename":"human_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:41.305000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000036/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000036/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.903678","modified":"2024-05-17T11:23:50.018Z","version":"v-0.0.0"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Protein Citations dataset contains publication information for Mus musculus [taxid:10090] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7e2eb7a286cf1db529a21de813b39d9b4af22740ec8920184cdf5decd5b9d493","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_citations_uniprotkb.stat.csv","filename":"mouse_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":416,"last_update":"2024-05-17T11:23:50.018941Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000036/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000036/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.903678","modified":"2022-09-26T08:48:18.857788","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv","filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Citations dataset contains publication information for mouse [taxid:10090] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"fb9b8e788d96e217c94540ad65588cd4b5c1edae6e0be77c0090a75c7f1eb383","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_uniprotkb.stat.csv","filename":"mouse_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.086000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000036/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000036/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.903678","modified":"2022-09-26T08:48:18.857788","version":"v-2.1.1"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv","filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Citations dataset contains publication information for mouse [taxid:10090] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1b4d41043ee0d15b9ac32dd32b535208","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_uniprotkb.stat.csv","filename":"mouse_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:41.499000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000038/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000038/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f8265c184f7db995547428875fc0f7eac35caa90cf0061d02f879e4accaedbce","provenance_domain":{"name":"Human Glycosylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.905721","modified":"2024-12-10T16:55:51.406Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites (UniProtKB) dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Homo sapiens proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":333,"last_update":"2024-12-10T16:55:51.406599Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000038/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000038/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.905721","modified":"2022-09-26T08:48:18.850199","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7b0218fd8246b393e512d2dd49534aff3eb274bfd39e0f1f8287bee074d1a7b1","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.117000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000038/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000038/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.905721","modified":"2022-09-26T08:48:18.850199","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"5f5d7352df9b0a8527713776bcc24911","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:41.698000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000039/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000039/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a17923c0f50229b6fad5da42b39ecf8a738e7ea56ea18adeaab3c9bb39430187","provenance_domain":{"name":"Mouse Glycosylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.906744","modified":"2024-12-10T17:38:46.386Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Sites (UniProtKB) dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Mus musculus proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":335,"last_update":"2024-12-10T17:38:46.386855Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000039/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000039/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.906744","modified":"2022-09-26T08:48:18.839045","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0746c6465f3ded2541b29167e793c3a32cde686bd7e1bb3ab0c6d6a6a764fcb8","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.319000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000039/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000039/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.906744","modified":"2022-09-26T08:48:18.839045","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f33784e60443e214d0bafe5e32327ad0","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:41.889000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000040/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000040/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f470e25a9a8e232f2cebd377a513d87d1cfbd9005a47dbbc8562cd496182d16c","provenance_domain":{"name":"Glycosylation Sites - UniCarbKB [Human proteins]","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.907769","modified":"2024-12-05T19:01:21.578Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["List of Homo sapeins [taxid:9606] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file ;for script:human_glycosylation_current.csv) was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}],"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":447,"last_update":"2024-12-05T19:01:21.578057Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000040/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000040/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation Sites - UniCarbKB [Human proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.907769","modified":"2022-09-26T08:48:18.854947","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/human_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/human_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.2.log"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file ;for script:human_glycosylation_current.csv) was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)."],"etag":"41f1c5c303b8e4f978fac7883ae22d82130b64437a6589ae457daff87c2441f7","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.218000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000040/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000040/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation Sites - UniCarbKB [Human proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.907769","modified":"2022-09-26T08:48:18.854947","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/human_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/human_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.2.log"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file ;for script:human_glycosylation_current.csv) was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)."],"etag":"e33d474b6db84c32ec1f5df985071434","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:42.080000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000041/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000041/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c89a5c9f47db1fedc4a4a53f87c1dbbf66352fa93570c1dc29372bb541b2e1c2","provenance_domain":{"name":"Glycosylation sites - UniCarbKB [Mouse proteins]","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.908793","modified":"2024-12-05T19:02:01.346Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["List of Mus musculus [taxid:10090] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000007)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}],"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":449,"last_update":"2024-12-05T19:02:01.346647Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000041/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000041/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation sites - UniCarbKB [Mouse proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.908793","modified":"2022-09-26T08:48:18.860178","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/mouse_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/mouse_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.2.log"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000007)."],"etag":"281acb1d05a84c96bb3226b6905e1c33cda2023dcd81dd75d3ef46ea9e55fe63","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.167000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000041/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000041/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation sites - UniCarbKB [Mouse proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.908793","modified":"2022-09-26T08:48:18.860178","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/mouse_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/mouse_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.2.log"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000007)."],"etag":"24360f83d10e32d6068e24d7b21beef1","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:42.344000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000042/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000042/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d8924b847b82c9dc2473e73de6542b0889965c96c6ae2ae57a0f7a7bcd19343f","provenance_domain":{"name":"Human Glycosylation Sites (RCSB PDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.909814","modified":"2026-08-19T09:57:19.444Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites (RCSB PDB) dataset contains Homo sapiens [taxid:9606] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"input_list":[]}],"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_pdb.stat.csv","filename":"human_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2026-08-19T09:57:19.444399Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000042/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000042/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (RCSB PDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.909814","modified":"2022-09-26T08:48:18.837668","version":"v-2.0.2"},"description_domain":{"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/N-linked-ARG-details","filename":"N-linked-ARG-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/N-linked-ASN","filename":"N-linked-ASN-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-ASP","filename":"O-linked-ASP-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-GLU","filename":"O-linked-GLU-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-SER","filename":"O-linked-SER-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-THR","filename":"O-linked-THR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-TYR","filename":"O-linked-TYR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosylation Sites (RCSB PDB) dataset contains human [taxid:9606] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"etag":"b905fbcd8d6cc4b4a71e845c9ae7a204d57af871f5fd8ba7f647aed723786519","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"N-linked-ARG-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.stat.csv","filename":"human_proteoform_glycosylation_sites_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.849000Z","access_count":38},{"object_id":"https://biocomputeobject.org/GLY_000042/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000042/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (RCSB PDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.909814","modified":"2022-09-26T08:48:18.837668","version":"v-2.1.1"},"description_domain":{"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/N-linked-ARG-details","filename":"N-linked-ARG-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/N-linked-ASN","filename":"N-linked-ASN-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-ASP","filename":"O-linked-ASP-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-GLU","filename":"O-linked-GLU-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-SER","filename":"O-linked-SER-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-THR","filename":"O-linked-THR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-TYR","filename":"O-linked-TYR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosylation Sites (RCSB PDB) dataset contains human [taxid:9606] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"etag":"737ca381344a6d0a9f0bd72011f6016a","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"N-linked-ARG-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.stat.csv","filename":"human_proteoform_glycosylation_sites_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:42.526000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000043/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000043/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7066854b5194e2de18eb311af265d469b8de3094807c0ca1dd8f0314a73e24e4","provenance_domain":{"name":"Mouse Glycosylation Sites (RCSB PDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.910839","modified":"2026-08-19T09:58:03.857Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Sites (RCSB PDB) dataset contains Mus musculus [taxid:10090] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}],"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":509,"last_update":"2026-08-19T09:58:03.857774Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000043/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000043/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (RCSB PDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.910839","modified":"2022-09-26T08:48:18.851493","version":"v-2.0.2"},"description_domain":{"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/N-linked-ARG","filename":"N-linked-ARG-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/N-linked-ASN","filename":"N-linked-ASN-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-ASP","filename":"O-linked-ASP-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-GLU","filename":"O-linked-GLU-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-SER","filename":"O-linked-SER-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-THR","filename":"O-linked-THR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-TYR","filename":"O-linked-TYR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"etag":"43c4189a9b14f4d9eed030c83730bc0ba4aa60ebefad931b1a9549b13f8bc325","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"N-linked-ARG-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.191000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000043/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000043/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (RCSB PDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.910839","modified":"2022-09-26T08:48:18.851493","version":"v-2.1.1"},"description_domain":{"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/N-linked-ARG","filename":"N-linked-ARG-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/N-linked-ASN","filename":"N-linked-ASN-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-ASP","filename":"O-linked-ASP-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-GLU","filename":"O-linked-GLU-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-SER","filename":"O-linked-SER-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-THR","filename":"O-linked-THR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-TYR","filename":"O-linked-TYR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"etag":"33c9e8b0437f5a62e5953601c390b4e0","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"N-linked-ARG-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:42.707000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000053/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000053/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.921192","modified":"2024-05-17T11:23:50.305Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Isoform sequences (UniProtKB) dataset contains Homo sapiens [taxid:9606] protein fasta sequences for the human isoform accessions from the UniProtKB database,. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"49c8916a938082767e0e51d61fc481008abfbf352af82a42c42053738201ae03","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_allsequences.stat.csv","filename":"human_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":268,"last_update":"2024-05-17T11:23:50.305212Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000053/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000053/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.921192","modified":"2022-09-26T08:48:18.833160","version":"v-2.0.2"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Isoform sequences (UniProtKB) dataset contains human [taxid:9606] protein fasta sequences for the human isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"abd8fc450f951c85f1f3f35b331206abd88f487cddbe92430d47f3aacd52177d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_allsequences.stat.csv","filename":"human_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.444000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000053/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000053/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.921192","modified":"2022-09-26T08:48:18.833160","version":"v-2.1.1"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Isoform sequences (UniProtKB) dataset contains human [taxid:9606] protein fasta sequences for the human isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"b061581b40fd03ca2fd0499cabac71e1","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_allsequences.stat.csv","filename":"human_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:42.885000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000054/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000054/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.921192","modified":"2024-05-17T11:23:50.344Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Isoform sequences (UniProtKB) dataset contains Mus musculus [taxid:10090] protein fasta sequences for the mouse isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"aa4e1dff7654385d4f66631b95212244d6fb3af660ff33f63816be97cefef18b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_allsequences.stat.csv","filename":"mouse_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":268,"last_update":"2024-05-17T11:23:50.344946Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000054/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000054/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.921192","modified":"2022-09-26T08:48:18.836405","version":"v-2.0.2"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Isoform sequences (UniProtKB) dataset contains mouse [taxid:10090] protein fasta sequences for the mouse isoform accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"606b425e15aa610fefd83e1dd299eec0275395a84d86884de49da2ca70b77739","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_allsequences.stat.csv","filename":"mouse_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.313000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000054/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000054/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.921192","modified":"2022-09-26T08:48:18.836405","version":"v-2.1.1"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Isoform sequences (UniProtKB) dataset contains mouse [taxid:10090] protein fasta sequences for the mouse isoform accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1658e2d738346f9a046d286812aaca65","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_allsequences.stat.csv","filename":"mouse_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:43.068000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000081/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000081/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.950210","modified":"2024-05-17T11:23:50.387Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Locus (Ensembl) contains Homo sapiens [taxid:9606] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"66c167c81c2ddac29f3607a662979109d1f189d013cd30ae4ee20876827401d7","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_genelocus.stat.csv","filename":"human_protein_genelocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":310,"last_update":"2024-05-17T11:23:50.387788Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000081/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000081/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.950210","modified":"2022-09-26T08:48:18.840078","version":"v-2.0.2"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Locus (Ensembl) contains human [taxid:9606] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"c300d929ffd687b8086af7e643c1e31e6538592ebc9044d529ca6378953c46e5","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"Homo_sapiens.GRCh38.95.gtf","uri":"https:/data.glygen.org/ln2downloads/ucsc/gtf/Homo_sapiens.GRCh38.95.gtf"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_genelocus.stat.csv","filename":"human_protein_genelocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.613000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000081/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000081/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.950210","modified":"2022-09-26T08:48:18.840078","version":"v-2.1.1"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Locus (Ensembl) contains human [taxid:9606] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"2252e69621f281497cee78d2a6dd5e63","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"Homo_sapiens.GRCh38.95.gtf","uri":"/data/shared/glyds/downloads/ucsc/gtf/Homo_sapiens.GRCh38.95.gtf"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_genelocus.stat.csv","filename":"human_protein_genelocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:43.262000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000082/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000082/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.950210","modified":"2024-05-17T11:23:50.430Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Locus dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions mapped to the corresponding ensembl gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"9a6b1c4cbe7ab90a618d622fcc890b420be0c292048c4a77d0e72b076a8947bd","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_genelocus.stat.csv","filename":"mouse_protein_genelocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":383,"last_update":"2024-05-17T11:23:50.430678Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000082/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000082/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.950210","modified":"2022-09-26T08:48:18.861939","version":"v-2.0.2"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Locus dataset contains mouse [taxid:10090] UniProtKB canonical accessions mapped to the corresponding ensembl gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e45c30ef67b2806389d6c79711748f5bc426fa46f9f78243b825a0b29ff073e2","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"Mus_musculus.GRCm38.95.gtf","uri":"https:/data.glygen.org/ln2downloads/ucsc/gtf/Mus_musculus.GRCm38.95.gtf"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_genelocus.stat.csv","filename":"mouse_protein_genelocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.253000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000082/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000082/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.950210","modified":"2022-09-26T08:48:18.861939","version":"v-2.1.1"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Locus dataset contains mouse [taxid:10090] UniProtKB canonical accessions mapped to the corresponding ensembl gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"3c318c6f3a8d9fd328d7992fff9cf8ce","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"Mus_musculus.GRCm38.95.gtf","uri":"/data/shared/glyds/downloads/ucsc/gtf/Mus_musculus.GRCm38.95.gtf"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genelocus.stat.csv","filename":"mouse_protein_genelocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:43.450000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000084/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000084/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cb15294a5ef0caa5db33d47fead41599e1a104a01e4d60f2d11d1799b4ad4b84","provenance_domain":{"name":"Human Protein Diseases (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.953432","modified":"2024-12-10T16:58:27.808Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Protein Diseases dataset contains list of Homo sapiens [taxid:9606] diseases from OMIM, MONDO and Genomics England databases mapped to the UniProtKB protein canonical accessions and Disease Ontology (DO) identifiers..","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship.","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest.","The Disease Ontology has been developed as a standardized ontology for human disease with the purpose of providing the biomedical community with consistent, reusable and sustainable descriptions of human disease terms, phenotype characteristics and related medical vocabulary disease concepts through collaborative efforts of biomedical researchers, coordinated by the University of Maryland School of Medicine, Institute for Genome Sciences.","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, DO, and EMBL-EBI-UniProt and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the OMIM phenotypes for UniProtKB accessions and MONDO disease information from human_glyco-phenotype_disease_curation_list_v12-18-74.csv and Genomics England disease data from . The script maps the UniProtKB accessions to the UniprotKB canonical accessions."}],"keywords":["disease","HPO","OMIM","Genomics England PanelApp","Monarch Initiative","MONDO","DO"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_uniprotkb.csv","filename":"human_protein_disease_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_uniprotkb.stat.csv","filename":"human_protein_disease_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases_UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1442,"last_update":"2024-12-10T16:58:27.808611Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000084/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000084/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases_UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Diseases (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-01-23T17:21:05.953432","modified":"2022-09-26T08:48:18.866373","version":"v-2.0.2"},"description_domain":{"keywords":["disease","HPO","OMIM","Genomics England PanelApp","Monarch Initiative","MONDO","DO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/protein_domap.csv","filename":"protein_domap.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_disease_uniprotkb.csv","filename":"human_protein_disease_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the OMIM phenotypes for UniProtKB accessions and MONDO disease information from human_glyco-phenotype_disease_curation_list_v12-18-74.csv and Genomics England disease data from . The script maps the UniProtKB accessions to the UniprotKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Diseases dataset contains list of human [taxid:9606] diseases from OMIM, MONDO and Genomics England databases mapped to the UniProtKB protein canonical accessions and Disease Ontology (DO) identifiers..","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship.","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest.","The Disease Ontology has been developed as a standardized ontology for human disease with the purpose of providing the biomedical community with consistent, reusable and sustainable descriptions of human disease terms, phenotype characteristics and related medical vocabulary disease concepts through collaborative efforts of biomedical researchers, coordinated by the University of Maryland School of Medicine, Institute for Genome Sciences.","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, DO, and EMBL-EBI-UniProt and GlyGen"],"etag":"ba6af00942a31e3753cc6d2cb2af9dd864a532c53671c0b457a58e2cc909e891","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"protein_disease_names.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_names.csv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"human_glyco-phenotype_disease_curation_list_v12-18-74.csv","uri":"https:/data.glygen.org/ln2downloads/ohsu/human_glyco-phenotype_disease_curation_list_v12-18-74.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_uniprotkb.csv","filename":"human_protein_disease_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_uniprotkb.stat.csv","filename":"human_protein_disease_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.144000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000084/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000084/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases_UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Diseases (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.953432","modified":"2022-09-26T08:48:18.866373","version":"v-2.1.1"},"description_domain":{"keywords":["disease","HPO","OMIM","Genomics England PanelApp","Monarch Initiative","MONDO","DO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/protein_domap.csv","filename":"protein_domap.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_disease_uniprotkb.csv","filename":"human_protein_disease_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the OMIM phenotypes for UniProtKB accessions and MONDO disease information from human_glyco-phenotype_disease_curation_list_v12-18-74.csv and Genomics England disease data from . The script maps the UniProtKB accessions to the UniprotKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Diseases dataset contains list of human [taxid:9606] diseases from OMIM, MONDO and Genomics England databases mapped to the UniProtKB protein canonical accessions and Disease Ontology (DO) identifiers..","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship.","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest.","The Disease Ontology has been developed as a standardized ontology for human disease with the purpose of providing the biomedical community with consistent, reusable and sustainable descriptions of human disease terms, phenotype characteristics and related medical vocabulary disease concepts through collaborative efforts of biomedical researchers, coordinated by the University of Maryland School of Medicine, Institute for Genome Sciences.","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, DO, and EMBL-EBI-UniProt and GlyGen"],"etag":"10c46aed3f9b1f83cc92eb3528247268","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"protein_disease_names.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_names.csv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"human_glyco-phenotype_disease_curation_list_v12-18-74.csv","uri":"/data/shared/glyds/downloads/ohsu/human_glyco-phenotype_disease_curation_list_v12-18-74.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_uniprotkb.csv","filename":"human_protein_disease_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_uniprotkb.stat.csv","filename":"human_protein_disease_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:43.662000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000087/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000087/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.956673","modified":"2024-05-21T13:52:10.676Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human Protein Recommended Names (UniProtKB) dataset contains Homo sapiens [taxid:9606]  UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"2a6222afc77d96d336cf47b8bed09e47c9ad394dfdafa60af867855bcb46f9b0","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_recnames.stat.csv","filename":"human_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":224,"last_update":"2024-05-21T13:52:10.676017Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000087/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000087/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.956673","modified":"2022-09-26T08:48:18.828019","version":"v-2.0.2"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for human [taxid:9606] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f655251b093b4860e0f6e2cd3c5cd65558bf924d1f999f193c9ec28c191f3508","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_recnames.stat.csv","filename":"human_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.610000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000087/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000087/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.956673","modified":"2022-09-26T08:48:18.828019","version":"v-2.1.1"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for human [taxid:9606] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"ffa70381890067f0ef00502b76db549c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_recnames.stat.csv","filename":"human_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:43.862000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000088/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000088/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.957692","modified":"2024-05-21T13:52:42.866Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Protein Recommended Names (UniProtKB) dataset contains Mus musculus [taxid:10090] UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d3de5852a7a05f636030cbd609f873450b4442316ac38dc65f563238a0a0e620","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_recnames.stat.csv","filename":"mouse_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":224,"last_update":"2024-05-21T13:52:42.866458Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000088/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000088/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.957692","modified":"2022-09-26T08:48:18.870276","version":"v-2.0.2"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for mouse [taxid:10090] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d7b9dba75c405e694519a5a69da7e1c654f8318d9a8a21a2332a0b388fd4f13e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_recnames.stat.csv","filename":"mouse_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.211000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000088/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000088/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.957692","modified":"2022-09-26T08:48:18.870276","version":"v-2.1.1"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for mouse [taxid:10090] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"eb7e317f8a41de3f2f2b0d9ef97a405a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_recnames.stat.csv","filename":"mouse_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:44.042000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000090/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000090/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2024-05-17T11:23:50.588Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Bgee dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"etag":"e4f297732e1a7bc5168f0ff2024ec9279d770183aff69871f9d39f08c7f6c789","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_bgee.stat.csv","filename":"human_protein_xref_bgee.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":471,"last_update":"2024-05-17T11:23:50.588559Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000090/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000090/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:48:18.831928","version":"v-2.0.2"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Bgee dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"etag":"953575a215a813518b301d3240ac65473b5d99ca45d28fd0f7ffa0b32c71fb49","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_bgee.stat.csv","filename":"human_protein_xref_bgee.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.186000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000090/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000090/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:48:18.831928","version":"v-2.1.1"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Bgee dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"etag":"713b3ae7daac3d1baea321289a650d3d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_bgee.stat.csv","filename":"human_protein_xref_bgee.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:44.227000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000091/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000091/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2024-05-17T11:23:50.627Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Bgee contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets"],"etag":"5c4a2a1107d67253cbfa6f102dcade2c8a2de21805c286513086b01e516e1e59","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_bgee.stat.csv","filename":"mouse_protein_xref_bgee.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":462,"last_update":"2024-05-17T11:23:50.627935Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000091/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000091/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:48:18.828977","version":"v-2.0.2"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Bgee contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets"],"etag":"a82c9d7e5b159bf8fdec13c268001dd2d45ac7b769bd3f1e2166583fff6ea2ee","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_bgee.stat.csv","filename":"mouse_protein_xref_bgee.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.156000Z","access_count":37},{"object_id":"https://biocomputeobject.org/GLY_000091/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000091/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:48:18.828977","version":"v-2.1.1"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Bgee contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets"],"etag":"00d6e2df4f449addda64db71ee0db1ff","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_bgee.stat.csv","filename":"mouse_protein_xref_bgee.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:44.422000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000092/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000092/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ac2d4cd1b3fac481a8509042d6cd7725dcb2aea2d1f4956ef075699f8d7dc266","provenance_domain":{"name":"Human UniProtKB Xref BioMuta","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T11:44:11.813164","modified":"2024-12-10T16:59:08.732Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniprotKB Xref BioMuta contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to BioMuta database accessions/identifiers. BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates. The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BioMuta database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["mutation","BioMuta","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_biomuta.stat.csv","filename":"human_protein_xref_biomuta.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Biomuta","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":709,"last_update":"2024-12-10T16:59:08.732644Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000092/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000092/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Biomuta","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref BioMuta","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T11:44:11.813164","modified":"2022-09-26T08:48:18.867570","version":"v-2.0.2"},"description_domain":{"keywords":["mutation","BioMuta","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BioMuta database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref BioMuta contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BioMuta database accessions/identifiers. BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates. The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"66a577a01b65a96326a4a9ed1ddb5ca30a2a0dae55583e7ac5c6d81f28614b5d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_biomuta.stat.csv","filename":"human_protein_xref_biomuta.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.180000Z","access_count":39},{"object_id":"https://biocomputeobject.org/GLY_000092/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000092/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Biomuta","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref BioMuta","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T11:44:11.813164","modified":"2022-09-26T08:48:18.867570","version":"v-2.1.1"},"description_domain":{"keywords":["mutation","BioMuta","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BioMuta database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref BioMuta contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BioMuta database accessions/identifiers. BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates. The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"6bf8e1b339eb454110f4560160bc0840","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_mutation_cancer.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_biomuta.stat.csv","filename":"human_protein_xref_biomuta.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:44.590000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000093/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000093/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.961796","modified":"2024-05-17T11:23:50.707Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref BRENDA contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"a714327fcfe353bc2dcb16bd08a674d116e0d378ea7f81d61ba4c4ed40e6ad53","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_brenda.stat.csv","filename":"human_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":476,"last_update":"2024-05-17T11:23:50.707650Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000093/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000093/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.961796","modified":"2022-09-26T08:48:18.865182","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref BRENDA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"229b0eadbecb8861f368c8fb1a856357f618059bbbdd1153b7b9882b4c447668","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_brenda.stat.csv","filename":"human_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.347000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000093/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000093/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.961796","modified":"2022-09-26T08:48:18.865182","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref BRENDA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"a94c243af5060f3c9117826a426e33da","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_brenda.stat.csv","filename":"human_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:44.772000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000094/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000094/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.961796","modified":"2024-05-17T11:23:50.749Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref BRENDA contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories.  It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"730a9dd44b754bd3a9caaad60831af059e766e3464208795e91b565c976a3e8a","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_brenda.stat.csv","filename":"mouse_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":478,"last_update":"2024-05-17T11:23:50.749771Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000094/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000094/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.961796","modified":"2022-09-26T08:48:18.863105","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref BRENDA contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories.  It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"a6d2e356deb4a9711503200e6d50b13d1203b6f6662442e03bb2387ac97e99d2","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_brenda.stat.csv","filename":"mouse_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.133000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000094/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000094/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.961796","modified":"2022-09-26T08:48:18.863105","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref BRENDA contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories.  It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"17354eaabee31ade20fd399de6afbe4d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_brenda.stat.csv","filename":"mouse_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:44.968000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000095/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000095/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2024-05-17T11:23:50.789Z","version":"v-0.0.0"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref CAZy contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"etag":"7707abc3b5162c55317ad54c5dc10c4f94e34c9e8d39ddbe18ca37bc8a5fd106","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_cazy.stat.csv","filename":"human_protein_xref_cazy.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":465,"last_update":"2024-05-17T11:23:50.789550Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000095/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000095/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:48:18.853269","version":"v-2.0.2"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref CAZy contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"etag":"015cf274bf4630188158ba220450cea4afa3dd399d3d873ba2fb059e5dd7178a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_cazy.stat.csv","filename":"human_protein_xref_cazy.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.117000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000095/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000095/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:48:18.853269","version":"v-2.1.1"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref CAZy contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"etag":"cbb17544377df97eb493a6045eb3e40f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_cazy.stat.csv","filename":"human_protein_xref_cazy.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:45.157000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000096/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000096/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2024-05-17T11:23:50.826Z","version":"v-0.0.0"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref CAZy contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates"],"etag":"5b8f1ea715ca2a330fa8a7a1f77b576e72f5005aee5b5dd2935b20c699b7e70e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_cazy.stat.csv","filename":"mouse_protein_xref_cazy.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":465,"last_update":"2024-05-17T11:23:50.826631Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000096/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000096/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:48:18.848605","version":"v-2.0.2"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref CAZy contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates"],"etag":"763505f8a9a4d1aabf393a6aba2de080fe271dd14a7b97be3f0e8e86769dda0b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_cazy.stat.csv","filename":"mouse_protein_xref_cazy.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:53.678000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000096/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000096/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:48:18.848605","version":"v-2.1.1"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref CAZy contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates"],"etag":"c77a1ff9ce41eda20028cc1306e27f9a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_cazy.stat.csv","filename":"mouse_protein_xref_cazy.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:45.338000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000097/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000097/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:09:02.680538","modified":"2024-05-17T11:23:50.868Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref CDD contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"etag":"f40faabca6578e781d40f56ec70d1593e6aadb2755c667815db75adf5a0f7fb9","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_cdd.stat.csv","filename":"human_protein_xref_cdd.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":420,"last_update":"2024-05-17T11:23:50.868067Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000097/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000097/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:09:02.680538","modified":"2022-09-26T08:48:18.841071","version":"v-2.0.2"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref CDD contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"etag":"57a40a4fb6c1023ff1486e1d96abb36e07c1598733c379e713590192b4812021","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_cdd.stat.csv","filename":"human_protein_xref_cdd.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.352000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000097/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000097/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:09:02.680538","modified":"2022-09-26T08:48:18.841071","version":"v-2.1.1"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref CDD contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"etag":"8e3bbe53a1b6e6f068bafd60e5cc06cc","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_cdd.stat.csv","filename":"human_protein_xref_cdd.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:45.531000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000098/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000098/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:09:02.680538","modified":"2024-05-17T11:23:50.909Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref CDD contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"etag":"faf8b874e36aac40b6e51241364564fe70be145198637fb427790e237c9ea317","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_cdd.stat.csv","filename":"mouse_protein_xref_cdd.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2024-05-17T11:23:50.909846Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000098/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000098/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:09:02.680538","modified":"2022-09-26T08:48:18.859043","version":"v-2.0.2"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref CDD contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"etag":"907fae2585b5653efaefbde5f9f027c43b982863fc8d86ae6abed6eee3478aaf","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_cdd.stat.csv","filename":"mouse_protein_xref_cdd.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.938000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000098/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000098/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:09:02.680538","modified":"2022-09-26T08:48:18.859043","version":"v-2.1.1"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref CDD contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"etag":"f6e66c640a46dd3b0c19787f94542611","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_cdd.stat.csv","filename":"mouse_protein_xref_cdd.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:45.719000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000099/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000099/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:09:44.596916","modified":"2024-05-17T11:23:50.950Z","version":"v-0.0.0"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref ChEMBL contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"295ca5e696b06807563755ef6e8388a4373c7e161a2d3789822934381005730e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_chembl.stat.csv","filename":"human_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-17T11:23:50.950703Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000099/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000099/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:09:44.596916","modified":"2022-09-26T08:48:18.856580","version":"v-2.0.2"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref ChEMBL contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"ec9b31d87ad90f7badb5e50b06e218ad4bea4f7b20a8d090bb821cf8aff67c56","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_chembl.stat.csv","filename":"human_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.023000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000099/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000099/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:09:44.596916","modified":"2022-09-26T08:48:18.856580","version":"v-2.1.1"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref ChEMBL contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"333a7619b683ecbd4d9b3acae92f80e7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_chembl.stat.csv","filename":"human_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:45.904000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000100/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000100/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:09:44.596916","modified":"2024-05-17T11:23:50.990Z","version":"v-0.0.0"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref ChEMBL contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"8488dcb87874e040eaf48dbd76e1c2dadeac97e0087d0735f10f21c3d9208da8","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_chembl.stat.csv","filename":"mouse_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-17T11:23:50.990925Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000100/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000100/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:09:44.596916","modified":"2022-09-26T08:56:48.459129","version":"v-2.0.2"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref ChEMBL contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"735686803697ff718f0957d4f95172519ec8eec9222e11384fb40cbfa4af44bf","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_chembl.stat.csv","filename":"mouse_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.040000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000100/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000100/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:09:44.596916","modified":"2022-09-26T08:56:48.459129","version":"v-2.1.1"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref ChEMBL contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"ef7c62b476a546483b8d3715f8ac6738","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_chembl.stat.csv","filename":"mouse_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:46.090000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000101/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000101/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Genecards cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref GeneCards","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:10:45.775261","modified":"2024-05-17T11:23:51.030Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene","GeneCards","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to GeneCards database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref GeneCards contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to GeneCards database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," GeneCards is a searchable, integrative database that provides comprehensive, user-friendly information on all annotated and predicted human genes. It automatically integrates gene-centric data from ~150 web sources, including genomic, transcriptomic, proteomic, genetic, clinical and functional information."],"etag":"b1104ab5fb85f4e2a16b3d710758b392482e8a970ac6c40fefcc171a793ef9d0","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_genecards.stat.csv","filename":"human_protein_xref_genecards.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":562,"last_update":"2024-05-17T11:23:51.030742Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000101/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000101/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Genecards cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref GeneCards","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:10:45.775261","modified":"2022-09-26T08:56:48.457177","version":"v-2.0.2"},"description_domain":{"keywords":["gene","GeneCards","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to GeneCards database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref GeneCards contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to GeneCards database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," GeneCards is a searchable, integrative database that provides comprehensive, user-friendly information on all annotated and predicted human genes. It automatically integrates gene-centric data from ~150 web sources, including genomic, transcriptomic, proteomic, genetic, clinical and functional information."],"etag":"ba6d93847c7614cef1ba38f1395e39259b1309ea05fabc76ac9800ff3ad7d42d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_genecards.stat.csv","filename":"human_protein_xref_genecards.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.155000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000101/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000101/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Genecards cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref GeneCards","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:10:45.775261","modified":"2022-09-26T08:56:48.457177","version":"v-2.1.1"},"description_domain":{"keywords":["gene","GeneCards","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to GeneCards database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref GeneCards contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to GeneCards database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," GeneCards is a searchable, integrative database that provides comprehensive, user-friendly information on all annotated and predicted human genes. It automatically integrates gene-centric data from ~150 web sources, including genomic, transcriptomic, proteomic, genetic, clinical and functional information."],"etag":"59fa70fa35b128f94a11f59e22daeca7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_genecards.stat.csv","filename":"human_protein_xref_genecards.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:46.273000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000102/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000102/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hgnc cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref HGNC","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:12:30.919588","modified":"2024-05-17T11:23:51.070Z","version":"v-0.0.0"},"description_domain":{"keywords":["HGNC","gene symbol","gene name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to HGNC database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref HGNC dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to HGNC accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The HUGO Gene Nomenclature Committee is a committee of the Human Genome Organization that sets the standards for human gene nomenclature. The HGNC approves a unique and meaningful name for every known human gene, based on a query of experts. "],"etag":"f616c3dee723cfee6ad9602b3ebfc441dd1eab3f33d000c8b34ded699a28957c","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_hgnc.stat.csv","filename":"human_protein_xref_hgnc.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":487,"last_update":"2024-05-17T11:23:51.070300Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000102/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000102/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hgnc cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref HGNC","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:12:30.919588","modified":"2022-09-26T08:56:48.522560","version":"v-2.0.2"},"description_domain":{"keywords":["HGNC","gene symbol","gene name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to HGNC database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref HGNC dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to HGNC accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The HUGO Gene Nomenclature Committee is a committee of the Human Genome Organization that sets the standards for human gene nomenclature. The HGNC approves a unique and meaningful name for every known human gene, based on a query of experts. "],"etag":"5cfca89d2fd0c28df43d842b598c4ace719b9a583638975c929fc1d74b02a779","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_hgnc.stat.csv","filename":"human_protein_xref_hgnc.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.108000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000102/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000102/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hgnc cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref HGNC","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:12:30.919588","modified":"2022-09-26T08:56:48.522560","version":"v-2.1.1"},"description_domain":{"keywords":["HGNC","gene symbol","gene name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to HGNC database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref HGNC dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to HGNC accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The HUGO Gene Nomenclature Committee is a committee of the Human Genome Organization that sets the standards for human gene nomenclature. The HGNC approves a unique and meaningful name for every known human gene, based on a query of experts. "],"etag":"3b9766acf821f2339a1610abfd08b796","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.stat.csv","filename":"human_protein_xref_hgnc.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:46.454000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000103/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000103/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Mgi cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref MGI","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2024-05-17T11:23:51.109Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene symbol","gene name","MGI","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to MGI database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref MGI contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to MGI database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","MGI is the international database resource for the laboratory mouse, providing integrated genetic, genomic, and biological data to facilitate the study of mouse health and disease."],"etag":"ef558aa2dcbfaa3bca21060e0afd3c0ff99e26c2dbdcb88a16e79db57990e48b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_mgi.stat.csv","filename":"mouse_protein_xref_mgi.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":423,"last_update":"2024-05-17T11:23:51.109610Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000103/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000103/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Mgi cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref MGI","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2022-09-26T08:56:48.514114","version":"v-2.0.2"},"description_domain":{"keywords":["gene symbol","gene name","MGI","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to MGI database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref MGI contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to MGI database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","MGI is the international database resource for the laboratory mouse, providing integrated genetic, genomic, and biological data to facilitate the study of mouse health and disease."],"etag":"8d4bfe119ca93f8ee99851a5bc36179a642a2588303f528c27557425769c0e6a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_mgi.stat.csv","filename":"mouse_protein_xref_mgi.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.474000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000103/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000103/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Mgi cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref MGI","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2022-09-26T08:56:48.514114","version":"v-2.1.1"},"description_domain":{"keywords":["gene symbol","gene name","MGI","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to MGI database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref MGI contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to MGI database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","MGI is the international database resource for the laboratory mouse, providing integrated genetic, genomic, and biological data to facilitate the study of mouse health and disease."],"etag":"f966e7b1ae124fdda6ac42566293ebe6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_mgi.stat.csv","filename":"mouse_protein_xref_mgi.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:46.642000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000104/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000104/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2024-05-17T11:23:51.147Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref NCBI Gene dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"253c2259d03f8d50399fff880df8eb0cf4407702e4ebf0cadfcba9bc780c37ec","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_geneid.stat.csv","filename":"human_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":504,"last_update":"2024-05-17T11:23:51.147463Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000104/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000104/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2022-09-26T08:56:48.503378","version":"v-2.0.2"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref NCBI Gene dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"76ff2f2213b00943a1926d52ebad7a74534e84efbf30a058d9d929c6530d4272","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.stat.csv","filename":"human_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:15.108000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000104/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000104/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2022-09-26T08:56:48.503378","version":"v-2.1.1"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref NCBI Gene dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"73736b67d946e757ffa79d826af34bef","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.stat.csv","filename":"human_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:46.828000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000105/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000105/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2024-05-17T11:23:51.184Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref NCBI Gene dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide. "],"etag":"fd4d78fd28b65000ed85c7980d910cd843f0923594c57c1aaab61926b5fb5470","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_geneid.stat.csv","filename":"mouse_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":506,"last_update":"2024-05-17T11:23:51.184792Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000105/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000105/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2022-09-26T08:56:48.484844","version":"v-2.0.2"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref NCBI Gene dataset contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide. "],"etag":"7f1c69b22d08aed63eb20bceaa90030f5983b0a034b33f61156b8bd3d74196b7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_geneid.stat.csv","filename":"mouse_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.845000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000105/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000105/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:11:47.098435","modified":"2022-09-26T08:56:48.484844","version":"v-2.1.1"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref NCBI Gene dataset contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide. "],"etag":"2b552229596c8a763abb158f4dab821f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.stat.csv","filename":"mouse_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:47.006000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000106/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000106/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2024-05-17T11:23:51.222Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref InterPro contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"6a97ba0965aafdb4b60362d9b1f41e862e25d5b2be4c0d3c59418a66ff0b4fe9","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_interpro.stat.csv","filename":"human_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":463,"last_update":"2024-05-17T11:23:51.222779Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000106/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000106/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:56:48.478906","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref InterPro contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"97d8a81fbf07d315f05042326c76e39365a05673ae5d6ad81bb1f724b7d6e9ea","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_interpro.stat.csv","filename":"human_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.088000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000106/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000106/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:56:48.478906","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref InterPro contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"f3d4b36a2f1fcf8ac7b4d7fbe210fd97","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_interpro.stat.csv","filename":"human_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:47.194000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000107/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000107/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2024-05-17T11:23:51.261Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref InterPro contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterize them. "],"etag":"2c5b3668bf9cbc617fa29f67ea4a942cb7318790962ceffc80f6f88ec6abb8fd","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_interpro.stat.csv","filename":"mouse_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":467,"last_update":"2024-05-17T11:23:51.261558Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000107/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000107/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:56:48.468055","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref InterPro contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterize them. "],"etag":"4a91af682dd1ba17e29fb25687518d18c736f83afc78c4f550b4a6a8d867e1fb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_interpro.stat.csv","filename":"mouse_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.240000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000107/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000107/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T12:05:44.324142","modified":"2022-09-26T08:56:48.468055","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref InterPro contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterize them. "],"etag":"40ed406a669358c90228e4b7af805947","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_interpro.stat.csv","filename":"mouse_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:47.381000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000108/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000108/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2024-05-17T11:23:51.299Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref KEGG PATHWAY contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"etag":"b9e5674d5a4a0ed626b6a952ef002e1ac49f0cc57de70a574a3a06686e358b61","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_kegg.stat.csv","filename":"human_protein_xref_kegg.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":408,"last_update":"2024-05-17T11:23:51.299525Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000108/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000108/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.493813","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref KEGG PATHWAY contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"etag":"24babf15465b60785f02c4010f3cb9ee6fe7ba00bd6abb12e4b71198ba3544f6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_kegg.stat.csv","filename":"human_protein_xref_kegg.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.193000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000108/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000108/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.493813","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref KEGG PATHWAY contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"etag":"9407deeb612c5e42094852e3043236ab","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_kegg.stat.csv","filename":"human_protein_xref_kegg.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:47.566000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000109/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000109/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2024-05-17T11:23:51.339Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref KEGG PATHWAY contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"etag":"bd4653e949ec9afbf95889bcfc598e49b470e4bf0930ac2709ebef01b3dcc1d0","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_kegg.stat.csv","filename":"mouse_protein_xref_kegg.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":409,"last_update":"2024-05-17T11:23:51.339153Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000109/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000109/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.492384","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref KEGG PATHWAY contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"etag":"660ca61babe614b24686dcb661823806933044204a9089bac1a042b1203b7b78","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_kegg.stat.csv","filename":"mouse_protein_xref_kegg.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.724000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000109/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000109/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.492384","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref KEGG PATHWAY contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"etag":"0c7857dd44df5d8bebd500aee042d4b5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_kegg.stat.csv","filename":"mouse_protein_xref_kegg.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:47.750000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000110/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000110/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Omim cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMIM","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2024-05-17T11:23:51.376Z","version":"v-0.0.0"},"description_domain":{"keywords":["phenotype","genotype","OMIM","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMIM database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref OMIM contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to OMIM database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship."],"etag":"98e4206cd71b7b58b96ce4b40ad34ad915b47db9cd60fd8228dedd8c125efa7c","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_mim.stat.csv","filename":"human_protein_xref_mim.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":429,"last_update":"2024-05-17T11:23:51.376951Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000110/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000110/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Omim cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMIM","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.481082","version":"v-2.0.2"},"description_domain":{"keywords":["phenotype","genotype","OMIM","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMIM database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref OMIM contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMIM database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship."],"etag":"b367c055760646f711ae987b2d541064ac7b97ffeb735a113e6753929c5abb7d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_mim.stat.csv","filename":"human_protein_xref_mim.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.996000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000110/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000110/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Omim cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMIM","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.481082","version":"v-2.1.1"},"description_domain":{"keywords":["phenotype","genotype","OMIM","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMIM database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref OMIM contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMIM database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship."],"etag":"1ff173551034347ca829f8cb16c8ac29","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_mim.stat.csv","filename":"human_protein_xref_mim.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:47.934000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000112/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000112/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4f8ed749ef9f265138d52934097bcc0258e5d257efff9495b22ba02480496bf4","provenance_domain":{"name":"Human UniProtKB Xref neXtProt","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.959744","modified":"2025-10-08T15:07:20.780Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniprotKB Xref neXtProt contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to neXtProt database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","neXtProt is a comprehensive human-centric discovery platform, offering its users a seamless integration of and navigation through protein-related data.",null],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to neXtProt database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["neXtProt","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_nextprot.stat.csv","filename":"human_protein_xref_nextprot.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Nextprot cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":5,"last_update":"2025-10-08T15:07:20.780144Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000112/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000112/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Nextprot cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref neXtProt","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.501055","version":"v-2.0.2"},"description_domain":{"keywords":["neXtProt","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to neXtProt database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref neXtProt contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to neXtProt database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","neXtProt is a comprehensive human-centric discovery platform, offering its users a seamless integration of and navigation through protein-related data.",""],"etag":"6b6b93d71345cb10b41452147425ecc822d5d44bfbb1966216adb0601c0169bb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_nextprot.stat.csv","filename":"human_protein_xref_nextprot.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.885000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000112/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000112/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Nextprot cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref neXtProt","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.501055","version":"v-2.1.1"},"description_domain":{"keywords":["neXtProt","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to neXtProt database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref neXtProt contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to neXtProt database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","neXtProt is a comprehensive human-centric discovery platform, offering its users a seamless integration of and navigation through protein-related data.",""],"etag":"8e3cc5c01bf6ea506d707b10725f1155","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_nextprot.stat.csv","filename":"human_protein_xref_nextprot.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:48.121000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000113/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000113/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2024-05-17T11:23:51.451Z","version":"v-0.0.0"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref OMA contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"etag":"4d73c5df98c1c2a65023a96e42308fb916a085e5fc2341746846f87262d07bbb","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_oma.stat.csv","filename":"human_protein_xref_oma.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":358,"last_update":"2024-05-17T11:23:51.451840Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000113/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000113/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.486746","version":"v-2.0.2"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref OMA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"etag":"a4b9173f7f816dfcd2a0571a58fd2c1a84dddb546d0e51d322039aa2518c2fcb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_oma.stat.csv","filename":"human_protein_xref_oma.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.452000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000113/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000113/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.486746","version":"v-2.1.1"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref OMA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"etag":"23c78b939ea53f5080a497006994625d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oma.stat.csv","filename":"human_protein_xref_oma.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:48.310000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000114/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000114/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2024-05-17T11:23:51.490Z","version":"v-0.0.0"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref OMA contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"etag":"1fabc48edacc033ef69c1c4ad223b499e7e81c4d8171d82b027876c3483fbf54","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_oma.stat.csv","filename":"mouse_protein_xref_oma.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":359,"last_update":"2024-05-17T11:23:51.490223Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000114/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000114/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.518389","version":"v-2.0.2"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref OMA contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"etag":"16d86700188a4f26badd749cbbabd9fd9a691b71e2351da4e06d58eadc8720bb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_oma.stat.csv","filename":"mouse_protein_xref_oma.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.506000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000114/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000114/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-01-23T17:21:05.959744","modified":"2022-09-26T08:56:48.518389","version":"v-2.1.1"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref OMA contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"etag":"9adc1d2056c4843fcb5cfbbcf956f224","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oma.stat.csv","filename":"mouse_protein_xref_oma.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:48.486000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000115/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000115/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T14:55:58.596936","modified":"2024-05-17T11:23:51.528Z","version":"v-0.0.0"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref OrthoDB contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"etag":"9acbcb3f5ea458e929fa5322182d43f3cee00b7031e5066161bcb812a8329395","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_orthodb.stat.csv","filename":"human_protein_xref_orthodb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":424,"last_update":"2024-05-17T11:23:51.528651Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000115/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000115/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T14:55:58.596936","modified":"2022-09-26T08:56:48.516313","version":"v-2.0.2"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref OrthoDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"etag":"f01d8384cb98f2e530b84a17b88b4686dca358a39e500d818bdabbf2dac43447","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_orthodb.stat.csv","filename":"human_protein_xref_orthodb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.472000Z","access_count":51},{"object_id":"https://biocomputeobject.org/GLY_000115/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000115/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T14:55:58.596936","modified":"2022-09-26T08:56:48.516313","version":"v-2.1.1"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref OrthoDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"etag":"d94006e2605fc7060c52f4da3cd226a5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_orthodb.stat.csv","filename":"human_protein_xref_orthodb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:48.671000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000116/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000116/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T14:58:32.333977","modified":"2024-05-17T11:23:51.566Z","version":"v-0.0.0"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref OrthoDB contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"etag":"253bf80a2b420ee40c1fc6897792ee62f7b0aed98b7fe4b996cd0a0ba1fa6ad6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_orthodb.stat.csv","filename":"mouse_protein_xref_orthodb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":425,"last_update":"2024-05-17T11:23:51.566280Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000116/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000116/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T14:58:32.333977","modified":"2022-09-26T08:56:48.461098","version":"v-2.0.2"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref OrthoDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"etag":"933d221fe48c76faf077c480daa807a413f11e7d59f58cb75d8b352b9e201823","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_orthodb.stat.csv","filename":"mouse_protein_xref_orthodb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.620000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000116/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000116/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T14:58:32.333977","modified":"2022-09-26T08:56:48.461098","version":"v-2.1.1"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref OrthoDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"etag":"635cc8e42f3a547f24f4774d2909546b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_orthodb.stat.csv","filename":"mouse_protein_xref_orthodb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:48.858000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000117/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000117/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T15:04:33.347577","modified":"2024-05-17T11:23:51.605Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref PANTHER contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"etag":"821d28592aa7af22570fdd737a60caeda9d765e743fafdcbf2b2ea6db2415968","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_panther.stat.csv","filename":"human_protein_xref_panther.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":463,"last_update":"2024-05-17T11:23:51.605823Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000117/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000117/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T15:04:33.347577","modified":"2022-09-26T08:56:48.455309","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref PANTHER contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"etag":"794224cb7e74637174555d25f083a0671cefaf2c9378b507ad325c0c97fc34e8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_panther.stat.csv","filename":"human_protein_xref_panther.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.047000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000117/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000117/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T15:04:33.347577","modified":"2022-09-26T08:56:48.455309","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref PANTHER contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"etag":"aa4b2cac132a821e025a5c3206abca83","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_panther.stat.csv","filename":"human_protein_xref_panther.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:49.047000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000118/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000118/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T15:06:27.574866","modified":"2024-05-17T11:23:51.643Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref PANTHER contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products. "],"etag":"95f5dbc5a168df0fe39bc28d32be7d2a11f609f1f027c985e52615ca564050a5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_panther.stat.csv","filename":"mouse_protein_xref_panther.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":467,"last_update":"2024-05-17T11:23:51.643723Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000118/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000118/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T15:06:27.574866","modified":"2022-09-26T08:56:48.526479","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref PANTHER contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products. "],"etag":"4afc496b4884030da13915549cce12a762c9461599fd89f8d4a57a1e85270e55","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_panther.stat.csv","filename":"mouse_protein_xref_panther.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.981000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000118/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000118/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T15:06:27.574866","modified":"2022-09-26T08:56:48.526479","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref PANTHER contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products. "],"etag":"5f6d50e4b5cb1a69bfa76e016941d50b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_panther.stat.csv","filename":"mouse_protein_xref_panther.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:49.233000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000119/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000119/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T15:08:57.534471","modified":"2024-05-17T11:23:51.680Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref PDB contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"3abaac476ae542e2d671d3880e21dcf87399618d36fd9fa2ef5689b6779f7f5c","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pdb.stat.csv","filename":"human_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2024-05-17T11:23:51.680214Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000119/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000119/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T15:08:57.534471","modified":"2022-09-26T08:56:48.512043","version":"v-2.0.2"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref PDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"98ab59930a434eb84bc991eb7cec9cfeeb1cb31f293d1c749be9085a3b70bd01","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pdb.stat.csv","filename":"human_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.332000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000119/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000119/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T15:08:57.534471","modified":"2022-09-26T08:56:48.512043","version":"v-2.1.1"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref PDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"5fbac471e67c64518907ff0919406c8c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pdb.stat.csv","filename":"human_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:49.418000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000120/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000120/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T15:11:39.076274","modified":"2024-05-17T11:23:51.717Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref PDB contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"ed2358cd5171113a686f9c3037d0445f411e76efacc73fa03eaf4fc12ffb161a","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_pdb.stat.csv","filename":"mouse_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2024-05-17T11:23:51.717443Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000120/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000120/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T15:11:39.076274","modified":"2022-09-26T08:56:48.465547","version":"v-2.0.2"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref PDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"7c25db85621e8bd076e3b4ed6f2992c25b8f3c3ebfd47392d726ff42cfdbdb1f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_pdb.stat.csv","filename":"mouse_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.031000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000120/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000120/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T15:11:39.076274","modified":"2022-09-26T08:56:48.465547","version":"v-2.1.1"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref PDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"e8be2166e38b0b026c3a213bda3638d4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_pdb.stat.csv","filename":"mouse_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:49.612000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000121/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000121/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T15:58:30.083377","modified":"2024-05-17T11:23:51.758Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Pfam contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"etag":"650324fa7309e45ccb54dd2948cda6e54e845a3fa4989ccb489940d6b01dfe01","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pfam.stat.csv","filename":"human_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":388,"last_update":"2024-05-17T11:23:51.758367Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000121/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000121/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T15:58:30.083377","modified":"2022-09-26T08:56:48.452992","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Pfam contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"etag":"00c51c78d09c6a3e9a94390ca58f6d37b87e856b2572136925949a9d0c037c1a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pfam.stat.csv","filename":"human_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.844000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000121/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000121/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T15:58:30.083377","modified":"2022-09-26T08:56:48.452992","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Pfam contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"etag":"4051a61499325cfb1ae8771d1c79d951","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pfam.stat.csv","filename":"human_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:49.793000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000122/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000122/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:01:50.980059","modified":"2024-05-17T11:23:51.799Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py . ","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Pfam contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"etag":"a642a0c901f3f5ed08fb366e3804c832bae36f7bf37d215ae5931d2da99b5d8d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_pfam.stat.csv","filename":"mouse_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2024-05-17T11:23:51.799967Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000122/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000122/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:01:50.980059","modified":"2022-09-26T08:56:48.529071","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py . ","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Pfam contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"etag":"3e8e42a4a694f9ba942fe19eb31762873c02f0e11abbe967979ccd9e58e58534","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_pfam.stat.csv","filename":"mouse_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.185000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000122/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000122/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:01:50.980059","modified":"2022-09-26T08:56:48.529071","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py . ","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Pfam contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"etag":"8116655ae5165c100307444e2d35a397","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_pfam.stat.csv","filename":"mouse_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:49.988000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000123/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000123/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:08:14.880048","modified":"2024-05-17T11:23:51.836Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref PRO contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"etag":"ce2517599e94def6d8b3f78bb409d2f10a3164b73095ca76e407cef84b069016","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pro.stat.csv","filename":"human_protein_xref_pro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":387,"last_update":"2024-05-17T11:23:51.836849Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000123/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000123/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:08:14.880048","modified":"2022-09-26T08:56:48.510012","version":"v-2.0.2"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref PRO contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"etag":"39106ab7e6fbf3d45654126d4ff98dd1cacf050b6b0bac46476fb47bc1de65bb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pro.stat.csv","filename":"human_protein_xref_pro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.218000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000123/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000123/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:08:14.880048","modified":"2022-09-26T08:56:48.510012","version":"v-2.1.1"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref PRO contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"etag":"dcf4d2d525f16b4ae7c8b99e977f27ed","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pro.stat.csv","filename":"human_protein_xref_pro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:50.210000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000124/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000124/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:10:07.474480","modified":"2024-05-17T11:23:51.876Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref PRO contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them.  "],"etag":"d5189be748f004f9d111571ced9b5b6bd595d5c84eff9b1d0985026663d842be","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_pro.stat.csv","filename":"mouse_protein_xref_pro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2024-05-17T11:23:51.876360Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000124/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000124/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:10:07.474480","modified":"2022-09-26T08:56:48.496178","version":"v-2.0.2"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref PRO contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them.  "],"etag":"2896c9c7f0f229a3d361e1a77ca833202a9c67b70477196d4d3e8095d7175692","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_pro.stat.csv","filename":"mouse_protein_xref_pro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.433000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000124/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000124/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:10:07.474480","modified":"2022-09-26T08:56:48.496178","version":"v-2.1.1"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref PRO contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them.  "],"etag":"bc250b283011bd16cb6407182e19d92a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_pro.stat.csv","filename":"mouse_protein_xref_pro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:50.397000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000125/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000125/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:14:06.456984","modified":"2024-05-17T11:23:51.915Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Reactome contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"8a3bbd4ffa23c80534850ad7ef9bbdcfcc1206f074544b8048a3bca446b8a882","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_reactome.stat.csv","filename":"human_protein_xref_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":346,"last_update":"2024-05-17T11:23:51.915106Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000125/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000125/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:14:06.456984","modified":"2022-09-26T08:56:48.490955","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Reactome contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"018aae9b2cb4504915c63c35a0842bc4606adcad9ed3493d264c922788e168aa","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_reactome.stat.csv","filename":"human_protein_xref_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.070000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000125/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000125/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:14:06.456984","modified":"2022-09-26T08:56:48.490955","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Reactome contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"a1aa52859138ed481e893020d2879999","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_reactome.stat.csv","filename":"human_protein_xref_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:50.586000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000126/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000126/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:16:23.633025","modified":"2024-05-17T11:23:51.956Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["TheMouse UniProtKB Xref Reactome contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"etag":"83e533aa4cf7dd0506606cb6a67e0501d0b531647860e0aa103bc0c480606b6f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_reactome.stat.csv","filename":"mouse_protein_xref_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":345,"last_update":"2024-05-17T11:23:51.956160Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000126/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000126/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:16:23.633025","modified":"2022-09-26T08:56:48.476514","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["TheMouse UniProtKB Xref Reactome contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"etag":"89376164dcfaecb7a026ef73a80fcecb9d3a9a28bb6047cb4901e872131e06d0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_reactome.stat.csv","filename":"mouse_protein_xref_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.011000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000126/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000126/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:16:23.633025","modified":"2022-09-26T08:56:48.476514","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["TheMouse UniProtKB Xref Reactome contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"etag":"5c7c9909f796b4120e21cdf3d19b92a5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_reactome.stat.csv","filename":"mouse_protein_xref_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:50.772000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000127/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000127/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:20:41.396963","modified":"2024-05-17T11:23:51.997Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref RefSeq contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"etag":"e3742bc4f9d5a223c181e80e708269a32916cb6e74e43f696e6b9d97a8137bfd","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_refseq.stat.csv","filename":"human_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":636,"last_update":"2024-05-17T11:23:51.997766Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000127/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000127/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:20:41.396963","modified":"2022-09-26T08:56:48.470055","version":"v-2.0.2"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref RefSeq contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"etag":"9151acabb78babc71c2d548e8b3e2a5dfe909d09b626fb53db51d49c59bc1a9f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.stat.csv","filename":"human_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.344000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000127/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000127/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:20:41.396963","modified":"2022-09-26T08:56:48.470055","version":"v-2.1.1"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniprotKB Xref RefSeq contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"etag":"461bab8c6fed249a4ece77eb8d667fc3","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.stat.csv","filename":"human_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:50.972000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000128/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000128/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:23:15.480143","modified":"2024-05-17T11:23:52.040Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref RefSeq contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"etag":"a7aeca2787345c3aed0987f98e37a7252460fbf222e9229b8a556c3ccbe8daad","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_refseq.stat.csv","filename":"mouse_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":636,"last_update":"2024-05-17T11:23:52.040087Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000128/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000128/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:23:15.480143","modified":"2022-09-26T08:56:48.505551","version":"v-2.0.2"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref RefSeq contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"etag":"d5981060902ad13e06243635e82342554a8938b4ef3559c037427d9993fb7673","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.stat.csv","filename":"mouse_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.685000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000128/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000128/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:23:15.480143","modified":"2022-09-26T08:56:48.505551","version":"v-2.1.1"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniprotKB Xref RefSeq contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"etag":"8881e51b063bfe6a31bb23ee53eb94b2","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.stat.csv","filename":"mouse_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:51.167000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000129/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000129/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T16:50:35.816502","modified":"2024-05-17T11:23:52.079Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref UniCarbKB contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"etag":"1d27a5592073d20d6541c053951f81b18a7e4d6148db79b6da29931d8eec8249","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_unicarbkb.stat.csv","filename":"human_protein_xref_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":411,"last_update":"2024-05-17T11:23:52.079932Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000129/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000129/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:50:35.816502","modified":"2022-09-26T08:56:48.483036","version":"v-2.0.2"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_mapping.csv","filename":"human_protein_mapping.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref UniCarbKB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"etag":"069e5995110c75e033983aa5291464903cc0987b2b4f586411a690b73b00e1e8","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_unicarbkb.stat.csv","filename":"human_protein_xref_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.707000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000129/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000129/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:50:35.816502","modified":"2022-09-26T08:56:48.483036","version":"v-2.1.1"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_mapping.csv","filename":"human_protein_mapping.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref UniCarbKB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"etag":"d7d2abcd41ea57ed71f2700cdbf374b4","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_unicarbkb.stat.csv","filename":"human_protein_xref_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:51.360000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000130/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000130/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"628888727bd992108589d753313842184944b51e903e66f6a9e1ff96fe25cd9b","provenance_domain":{"name":"Mouse UniProtKB Xref UniCarbKB","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T16:53:52.791212","modified":"2024-12-10T17:29:37.415Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse UniProtKB Xref UniCarbKB contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_unicarbkb.stat.csv","filename":"mouse_protein_xref_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":563,"last_update":"2024-12-10T17:29:37.415753Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000130/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000130/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T16:53:52.791212","modified":"2022-09-26T08:56:48.474302","version":"v-2.0.2"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref UniCarbKB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"1692b3e0449062e23fdb98f9cb70619a101a28e82335dbb652b60596cbbc1e2e","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_unicarbkb.stat.csv","filename":"mouse_protein_xref_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.170000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000130/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000130/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T16:53:52.791212","modified":"2022-09-26T08:56:48.474302","version":"v-2.1.1"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref UniCarbKB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"1bd6ae0157d20668cae82ea716fea4a8","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_unicarbkb.stat.csv","filename":"mouse_protein_xref_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:51.550000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000131/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000131/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T20:00:02.159427","modified":"2024-05-17T11:23:52.160Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Function (UniProtKB) dataset contains biological function annotation for Homo sapiens [taxid:9606] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"47ef410a9c8ff6643d63f1bec4304972dc48561c185b04d0bc64cfe78248fdfa","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_function_uniprotkb.csv","filename":"human_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_function_uniprotkb.stat.csv","filename":"human_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":257,"last_update":"2024-05-17T11:23:52.160331Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000131/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000131/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T20:00:02.159427","modified":"2022-09-26T08:56:48.472213","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_function_uniprotkb.csv","filename":"human_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Function (UniProtKB) dataset contains biological function annotation for human [taxid:9606] protein accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"ffd946e8763645beb8247470d8db1a2b8b66331503930de2fa588e350e756577","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_function_uniprotkb.csv","filename":"human_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_function_uniprotkb.stat.csv","filename":"human_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.297000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000131/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000131/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T20:00:02.159427","modified":"2022-09-26T08:56:48.472213","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_function_uniprotkb.csv","filename":"human_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Function (UniProtKB) dataset contains biological function annotation for human [taxid:9606] protein accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"3308437e3a2f7328996f7f2d50b0bcd8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_function_uniprotkb.csv","filename":"human_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_function_uniprotkb.stat.csv","filename":"human_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:51.741000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000132/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000132/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-15T20:02:44.685450","modified":"2024-05-17T11:23:52.199Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Function (UniProtKB) dataset contains biological function annotation for Mus musculus [taxid:10090] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"16477203353dec360a42caedf32399850bc25ad7fa7a090d7d5667b5c8b18e38","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_function_uniprotkb.csv","filename":"mouse_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_function_uniprotkb.stat.csv","filename":"mouse_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":258,"last_update":"2024-05-17T11:23:52.199472Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000132/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000132/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-15T20:02:44.685450","modified":"2022-09-26T08:56:48.498483","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_function_uniprotkb.csv","filename":"mouse_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Function (UniProtKB) dataset contains biological function annotation for mouse [taxid:10090] protein accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"624bdce58a0bbd5d193c69ea9ff8673e37f0eec51d1a7df512b881f68326e7f8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_function_uniprotkb.csv","filename":"mouse_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_function_uniprotkb.stat.csv","filename":"mouse_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.116000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000132/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000132/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-15T20:02:44.685450","modified":"2022-09-26T08:56:48.498483","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_function_uniprotkb.csv","filename":"mouse_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Function (UniProtKB) dataset contains biological function annotation for mouse [taxid:10090] protein accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"8b916f9d858bc9484ad3d4ba5d5aee7f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_function_uniprotkb.csv","filename":"mouse_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_function_uniprotkb.stat.csv","filename":"mouse_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:51.927000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000133/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000133/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (NCBI Refseq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-16T15:35:15.248632","modified":"2024-05-17T11:23:52.243Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Function (NCBI RefSeq) dataset contains biological function annotation of Homo sapiens [taxid:9606] genes from GeneRIF section in the NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"df63182d9688aeee698e2d4fcfc1fecac762da41d862fafa17d1812b37e22975","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_function_refseq.csv","filename":"human_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_function_refseq.stat.csv","filename":"human_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":259,"last_update":"2024-05-17T11:23:52.243092Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000133/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000133/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (NCBI Refseq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-16T15:35:15.248632","modified":"2022-09-26T08:56:48.489276","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Function (NCBI RefSeq) dataset contains biological function annotation of human [taxid:9606] genes from GeneRIF section in the NCBI RefSeq database. The dataset is downloaded from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"418dda00d9cc2b7c0e8085f8cfd64293fb99db43557026c949103db83bb6df88","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_9606.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_9606.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_function_refseq.csv","filename":"human_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_function_refseq.stat.csv","filename":"human_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.899000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000133/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000133/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (NCBI Refseq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-16T15:35:15.248632","modified":"2022-09-26T08:56:48.489276","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Function (NCBI RefSeq) dataset contains biological function annotation of human [taxid:9606] genes from GeneRIF section in the NCBI RefSeq database. The dataset is downloaded from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"7bd90e790ce0883371de3dae4aac51b8","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_9606.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_9606.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_function_refseq.csv","filename":"human_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_function_refseq.stat.csv","filename":"human_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:52.115000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000134/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000134/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (NCBI Refseq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-16T15:38:06.344586","modified":"2024-05-17T11:23:52.281Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1.0","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extract-from-gp.py extracts protein function information from NCBI RefSeq gpff format files and maps it to the UniProtKb canonical accessions for a final dataset output in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Function (NCBI RefSeq) dataset contains biological function annotation of Mus musulus [taxid:10090] genes from GeneRIF section in the NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"32eada946a9b4777f0c38d4fa2a9362c555ca35fad3b950bb33e6c64339e3394","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_function_refseq.stat.csv","filename":"mouse_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":259,"last_update":"2024-05-17T11:23:52.281684Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000134/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000134/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (NCBI Refseq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-16T15:38:06.344586","modified":"2022-09-26T08:56:48.530675","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1.0","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}],"prerequisite":[],"description":"The script extract-from-gp.py extracts protein function information from NCBI RefSeq gpff format files and maps it to the UniProtKb canonical accessions for a final dataset output in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Function (NCBI RefSeq) dataset contains biological function annotation of mouse [taxid:10090] genes from GeneRIF section in the NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"8d0e1d9295a7f0c0babaa89945d34396fb3f44e06cd542a72e30e3d1418df3fd","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10090.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_10090.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_function_refseq.stat.csv","filename":"mouse_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.921000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000134/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000134/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (NCBI Refseq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-16T15:38:06.344586","modified":"2022-09-26T08:56:48.530675","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1.0","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}],"prerequisite":[],"description":"The script extract-from-gp.py extracts protein function information from NCBI RefSeq gpff format files and maps it to the UniProtKb canonical accessions for a final dataset output in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Function (NCBI RefSeq) dataset contains biological function annotation of mouse [taxid:10090] genes from GeneRIF section in the NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"c5324c813c8a9443ed0ad26ae22f3ef5","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10090.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_10090.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_function_refseq.stat.csv","filename":"mouse_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:52.303000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000135/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000135/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"caddfe9d34d151d4eee08296582881d2512ae1700911238a3790ee6c96e2695c","provenance_domain":{"name":"Human Transcript Locus (Ensembl Transcript coordinates)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-16T16:05:08.939322","modified":"2024-12-10T14:39:30.565Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Transcript Locus (Ensembl Transcript coordinates)s dataset contains UniProtKB Homo sapiens[taxid:9606] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}],"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_transcriptlocus.stat.csv","filename":"human_protein_transcriptlocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":477,"last_update":"2024-12-10T14:39:30.565584Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000135/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000135/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-16T16:05:08.939322","modified":"2022-09-26T08:56:48.507984","version":"v-2.0.2"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlistcsv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB human [taxid:9606] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"b119b246d6f097643557ce98187156103e5cb0fc2ed132df767ab1b49d78aa3e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_transcriptlocus.stat.csv","filename":"human_protein_transcriptlocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.389000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000135/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000135/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-16T16:05:08.939322","modified":"2022-09-26T08:56:48.507984","version":"v-2.1.1"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlistcsv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB human [taxid:9606] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"495b101b842913a631245f994e0f9ef9","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_transcriptlocus.stat.csv","filename":"human_protein_transcriptlocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:52.488000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000136/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000136/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-03-16T16:06:41.833239","modified":"2024-05-17T11:23:52.363Z","version":"v-0.0.0"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Transcript Locus (Ensembl Transcript coordinates) contains UniProtKB Mus musculus [taxid:10090] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end positions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"a4aa19ef25c2dc926b6cc0fce1d37ccf43e0b08c657853e8199c3353a5ff0605","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_transcriptlocus.stat.csv","filename":"mouse_protein_transcriptlocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":388,"last_update":"2024-05-17T11:23:52.363121Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000136/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000136/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-03-16T16:06:41.833239","modified":"2022-09-26T08:56:48.463095","version":"v-2.0.2"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Transcript Locus (Ensembl Transcript coordinates) contains UniProtKB mouse [taxid:10090] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end positions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"19f948527182b717f633a6c4602e080b08ba39ef4f6df09ae7aac58d1f06bef5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_transcriptlocus.stat.csv","filename":"mouse_protein_transcriptlocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.878000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000136/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000136/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-03-16T16:06:41.833239","modified":"2022-09-26T08:56:48.463095","version":"v-2.1.1"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Transcript Locus (Ensembl Transcript coordinates) contains UniProtKB mouse [taxid:10090] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end positions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"b9bc997a295bff1352d5124d4f5c55d4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_transcriptlocus.stat.csv","filename":"mouse_protein_transcriptlocus.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:52.671000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000138/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000138/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2b357a7e50e857bef09b552f661e9502d51941cdc68a7c36d9da0b8efd4ef218","provenance_domain":{"name":"Human Proteoform Citations (UniCarbKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-04-16T16:31:37.511217","modified":"2024-12-10T16:59:53.015Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Proteoform Citations (UniCarbKB) contains Homo sapiens [taxid:9606] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}],"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":623,"last_update":"2024-12-10T16:59:53.015846Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000138/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000138/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (UniCarbKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-04-16T16:31:37.511217","modified":"2022-09-26T08:56:48.524643","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_unicarbkb.csv","filename":"human_proteoform_citations_glycosylation_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Proteoform Citations (UniCarbKB) contains human [taxid:9606] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"etag":"846035da1e32f9259f51e1655d05ce0c5e8b2639bf39e5e5e4c1df7c6deda1fb","io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/doi_citations.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_unicarbkb.csv","filename":"human_proteoform_citations_glycosylation_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_unicarbkb.stat.csv","filename":"human_proteoform_citations_glycosylation_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:53.156000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000138/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000138/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7fa950d60c6c5aec894d0fa12d719d88","provenance_domain":{"name":"Human Proteoform Citations (UniCarbKB)","version":"v-2.1.1","created":"2019-04-16T16:31:37.511217","modified":"2023-03-14T16:30:26.794Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Proteoform Citations (UniCarbKB) contains human [taxid:9606] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/doi_citations.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:53:52.853000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000139/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000139/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"876a62ed5aa83414b7d8553547ff541ce265e8b81aa56f05cb85b3b1ac03ff5d","provenance_domain":{"name":"Mouse Proteoform Citations (UniCarbKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-04-16T16:44:35.331041","modified":"2024-12-10T17:31:31.661Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Proteoform Citations (UniCarbKB) contains Mus musculus [taxid:10090] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}],"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":624,"last_update":"2024-12-10T17:31:31.661595Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000139/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000139/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteoform Citations (UniCarbKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-04-16T16:44:35.331041","modified":"2022-01-19T11:24:12.218378","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_unicarbkb.csv","filename":"mouse_proteoform_citations_glycosylation_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Proteoform Citations (UniCarbKB) contains mouse [taxid:10090] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. . The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"etag":"25c7bd40cfa88b6a26ff9fb117c3308f","io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/doi_citations.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_unicarbkb.csv","filename":"mouse_proteoform_citations_glycosylation_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_unicarbkb.stat.csv","filename":"mouse_proteoform_citations_glycosylation_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.756000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000139/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000139/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1c9f6e5ad6e90d25eccdbaebb2d58e7a","provenance_domain":{"name":"Mouse Proteoform Citations (UniCarbKB)","version":"v-2.1.1","created":"2019-04-16T16:44:35.331041","modified":"2023-03-14T16:32:35.904Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse Proteoform Citations (UniCarbKB) contains mouse [taxid:10090] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. . The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_unicarbkb.csv","filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/doi_citations.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:02.467000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000142/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000142/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c17fbb70be881be951907ae2ced522998024f9b2148903c701e2af36361ff1a4","provenance_domain":{"name":"Human Protein Glycosylation (Harvard Department of Chemistry and Chemical Biology)","version":"v-0.0.0","created":"2019-06-06T17:51:22.706056","modified":"2024-05-17T11:23:52.481Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Harvard University","contribution":["authoredBy","contributedBy"],"name":"Christina Woo","email":"cwoo@chemistry.harvard.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides information on O-glycosylation sites on Human proteins. The data is submitted by Dr.Christina Woo from Department of Chemistry and Chemical Biology, Harvard University. The GlyTouCan accession (G70994MS)is annotated to the glycan composition based on author's recommendation. Author's note: \"For the glycan assignment, it would be most technically correct to use a HexNAc molecule, although by and large, these are O-GlcNAc modifications, we cannot be 100% certain for every single one\". The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). The source publication:Woo CM, Lund PJ, Huang AC, Davis MM, Bertozzi CR, Pitteri SJ. Mapping and Quantification of Over 2000 O-linked Glycopeptides in Activated Human T Cells with Isotope-Targeted Glycoproteomics (Isotag). Mol Cell Proteomics. 2018;17(4):764-75. doi: 10.1074/mcp.RA117.000261. PubMed PMID: 29351928; PubMed Central PMCID: PMCPMC5880114)."],"description_domain":{"keywords":["Glycan","Publications","Proteoform"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was submitted by the author. An additional column \"Evidence\" with value \"GLYDS000142\" was added in the input file. A python script was used to process data to 1. map UniprotKB accessions to UniProtKB canonical accessions 2. Split the \"GlycoSite(s) (protein)\" column to amino acid and glycosylation site. 3.Split the \"GlycoSite(s) (protein)\" column into single value row. 4. Add two new columns: glycosylation_type=o-linked and evidence=29351928 (based on author's recommendation). A quality check is done to match the position + amino acid with the canonical fasta sequence (https://data.glygen.org/GLYDS000002). The rows which fail the QC are eliminated from the final output file."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_harvard.stat.csv","filename":"human_proteoform_glycosylation_sites_harvard.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""},{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation sites (Harvard)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":992,"last_update":"2024-05-17T11:23:52.481170Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000142/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000142/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation sites (Harvard)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation (Harvard Department of Chemistry and Chemical Biology)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Harvard University","contribution":["authoredBy","contributedBy","providedBy"],"name":"Christina Woo","email":"cwoo@chemistry.harvard.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-06-06T17:51:22.706056","modified":"2022-09-26T09:04:48.012276","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","Publications","Proteoform"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv","filename":"T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}],"prerequisite":[],"description":"The input file was submitted by the author. An additional column \"Evidence\" with value \"GLYDS000142\" was added in the input file. A python script was used to process data to 1. map UniprotKB accessions to UniProtKB canonical accessions 2. Split the \"GlycoSite(s) (protein)\" column to amino acid and glycosylation site. 3.Split the \"GlycoSite(s) (protein)\" column into single value row. 4. Add two new columns: glycosylation_type=o-linked and evidence=29351928 (based on author's recommendation). A quality check is done to match the position + amino acid with the canonical fasta sequence (https://data.glygen.org/GLYDS000002). The rows which fail the QC are eliminated from the final output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""},{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on O-glycosylation sites on Human proteins. The data is submitted by Dr.Christina Woo from Department of Chemistry and Chemical Biology, Harvard University. The GlyTouCan accession (G70994MS)is annotated to the glycan composition based on author's recommendation. Author's note: \"For the glycan assignment, it would be most technically correct to use a HexNAc molecule, although by and large, these are O-GlcNAc modifications, we cannot be 100% certain for every single one\". The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). The source publication:Woo CM, Lund PJ, Huang AC, Davis MM, Bertozzi CR, Pitteri SJ. Mapping and Quantification of Over 2000 O-linked Glycopeptides in Activated Human T Cells with Isotope-Targeted Glycoproteomics (Isotag). Mol Cell Proteomics. 2018;17(4):764-75. doi: 10.1074/mcp.RA117.000261. PubMed PMID: 29351928; PubMed Central PMCID: PMCPMC5880114)."],"etag":"1a79380ce4ed6adbce9ba359b8efaf2da6ba1c07f3f71182d5bdf626a0fcaaa6","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv","uri":"https:/data.glygen.org/ln2downloads/harvard/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.stat.csv","filename":"human_proteoform_glycosylation_sites_harvard.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:53.779000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000142/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000142/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"441a7cc41337f4b794c79788d9b4c3a5","provenance_domain":{"name":"Human Protein Glycosylation (Harvard Department of Chemistry and Chemical Biology)","version":"v-2.1.1","created":"2019-06-06T17:51:22.706056","modified":"2023-02-15T19:11:14.457Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Harvard University","contribution":["authoredBy","contributedBy"],"name":"Christina Woo","email":"cwoo@chemistry.harvard.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides information on O-glycosylation sites on Human proteins. The data is submitted by Dr.Christina Woo from Department of Chemistry and Chemical Biology, Harvard University. The GlyTouCan accession (G70994MS)is annotated to the glycan composition based on author's recommendation. Author's note: \"For the glycan assignment, it would be most technically correct to use a HexNAc molecule, although by and large, these are O-GlcNAc modifications, we cannot be 100% certain for every single one\". The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). The source publication:Woo CM, Lund PJ, Huang AC, Davis MM, Bertozzi CR, Pitteri SJ. Mapping and Quantification of Over 2000 O-linked Glycopeptides in Activated Human T Cells with Isotope-Targeted Glycoproteomics (Isotag). Mol Cell Proteomics. 2018;17(4):764-75. doi: 10.1074/mcp.RA117.000261. PubMed PMID: 29351928; PubMed Central PMCID: PMCPMC5880114)."],"description_domain":{"keywords":["Glycan","Publications","Proteoform"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv","filename":"T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}],"prerequisite":[],"description":"The input file was submitted by the author. An additional column \"Evidence\" with value \"GLYDS000142\" was added in the input file. A python script was used to process data to 1. map UniprotKB accessions to UniProtKB canonical accessions 2. Split the \"GlycoSite(s) (protein)\" column to amino acid and glycosylation site. 3.Split the \"GlycoSite(s) (protein)\" column into single value row. 4. Add two new columns: glycosylation_type=o-linked and evidence=29351928 (based on author's recommendation). A quality check is done to match the position + amino acid with the canonical fasta sequence (https://data.glygen.org/GLYDS000002). The rows which fail the QC are eliminated from the final output file."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv","uri":"/data/shared/glyds/downloads/harvard/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.stat.csv","filename":"human_proteoform_glycosylation_sites_harvard.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""},{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation sites (Harvard)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:02.649000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000143/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000143/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ae1bbf9dd1bbd211a550fa853013fd9dec9b99aa5d788f8f5b248a239337ea6c","provenance_domain":{"name":"Human Protein Glycosylation (Literature)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-06-14T14:54:26.195339","modified":"2024-12-10T16:47:37.700Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Winiewski, J. R., & Mann, M. (2012). Quantification of the N-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\").  The listed proteins (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000001). "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLY_000002) to generate the output files."}],"keywords":["proteins","canonical","glycosylation","literature","publications"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_literature.stat.csv","filename":"human_proteoform_glycosylation_sites_literature.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB publications","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":989,"last_update":"2024-12-10T16:47:37.700310Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000143/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000143/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB publications","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation (Literature)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-06-14T14:54:26.195339","modified":"2022-09-26T08:56:48.520442","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation","literature","publications"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycosylation_sites_24190977_s5.csv","filename":"glycosylation_sites_24190977_s5.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycosylation_sites_23090970_s5","filename":"glycosylation_sites_23090970_s5"},{"uri":",https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycosylation_sites_23090970_s2.csv","filename":"glycosylation_sites_23090970_s2.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLYDS000002)to generate the output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Winiewski, J. R., & Mann, M. (2012). Quantification of the N-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\").  The listed proteins (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). "],"etag":"c868192062fd25d702efc449f1e7fbb273241d3361b20ee21a5028a8a96ec9a1","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_sites_lit_23090970_s2.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_23090970_s2.csv"}},{"uri":{"filename":"glycosylation_sites_lit_23090970_s5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_23090970_s5.csv"}},{"uri":{"filename":"glycosylation_sites_lit_24190977_s5.cs","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_24190977_s5.cs"}},{"uri":{"filename":"glycosylation_sites_lit_x_sx.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_x_sx.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.stat.csv","filename":"human_proteoform_glycosylation_sites_literature.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.030000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000143/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000143/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB publications","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation (Literature)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-06-14T14:54:26.195339","modified":"2022-09-26T08:56:48.520442","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation","literature","publications"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycosylation_sites_24190977_s5.csv","filename":"glycosylation_sites_24190977_s5.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycosylation_sites_23090970_s5","filename":"glycosylation_sites_23090970_s5"},{"uri":",https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycosylation_sites_23090970_s2.csv","filename":"glycosylation_sites_23090970_s2.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLYDS000002)to generate the output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Winiewski, J. R., & Mann, M. (2012). Quantification of the N-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\").  The listed proteins (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). "],"etag":"80770715edf7bee13301014e361a9f06","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_sites_lit_23090970_s2.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_23090970_s2.csv"}},{"uri":{"filename":"glycosylation_sites_lit_23090970_s5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_23090970_s5.csv"}},{"uri":{"filename":"glycosylation_sites_lit_24190977_s5.cs","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_24190977_s5.cs"}},{"uri":{"filename":"glycosylation_sites_lit_x_sx.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_x_sx.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.stat.csv","filename":"human_proteoform_glycosylation_sites_literature.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:02.839000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000221/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000221/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"33b7bcd18db34de8157d2969b7ef3938f185fafb68d45bc4a947d2c3681e2a74","provenance_domain":{"name":"Glycosylation sites - UniCarbKB [Rat proteins]","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-05T14:34:59.005886","modified":"2024-12-05T19:02:39.985Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["List of Rattus norvegicus [taxid:10116] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000244)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","input_list":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid. "}],"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":455,"last_update":"2024-12-05T19:02:39.985024Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000221/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000221/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation sites - UniCarbKB [Rat proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-05T14:34:59.005886","modified":"2022-09-26T09:04:47.990993","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/rat_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"rat_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/rat_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"rat_proteoform_glycosylation_sites_unicarbkb.2.log"}],"prerequisite":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000244)."],"etag":"83ef190a3e8af8e8a6d4a2242e318fbdfd38f9b5351345cfd2860616c97d6e03","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.646000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000221/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000221/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation sites - UniCarbKB [Rat proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-05T14:34:59.005886","modified":"2022-09-26T09:04:47.990993","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/rat_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"rat_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/rat_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"rat_proteoform_glycosylation_sites_unicarbkb.2.log"}],"prerequisite":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000244)."],"etag":"303c405961242346d09cabbdedd9d064","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:03.024000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000222/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000222/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.950487","modified":"2024-05-17T11:23:52.596Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Recommended Names (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"b2c8ea4798a9e05ed6069317c7bac0c21c96746a7dde1fe2b55fc7bcc749cca7","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_recnames.csv","filename":"rat_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_recnames.stat.csv","filename":"rat_protein_recnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":229,"last_update":"2024-05-17T11:23:52.596710Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000222/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000222/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.950487","modified":"2022-09-26T09:04:47.939105","version":"v-2.0.2"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_recnames.csv","filename":"rat_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for rat [taxid:10116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"612e24a8a388233146516fee929c92fe505e9a82863e1b6dc9abd42111af8801","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_recnames.csv","filename":"rat_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_recnames.stat.csv","filename":"rat_protein_recnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.534000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000222/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000222/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.950487","modified":"2022-09-26T09:04:47.939105","version":"v-2.1.1"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_recnames.csv","filename":"rat_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for rat [taxid:10116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"a8bb235e122f26afa9e0068e6da08c1e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_recnames.csv","filename":"rat_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_recnames.stat.csv","filename":"rat_protein_recnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:03.210000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000223/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000223/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.951602","modified":"2024-05-17T11:23:52.632Z","version":"v-0.0.0"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Gene Ontology (GO) dataset contains Homo sapiens [taxid:9606] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"290f887e0801ced37d4b1c71e582d87ea35a4b455586fea783747c7add883cde","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_go_annotation.csv","filename":"human_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_go_annotation.stat.csv","filename":"human_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":263,"last_update":"2024-05-17T11:23:52.632793Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000223/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000223/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.951602","modified":"2022-09-26T09:04:47.947013","version":"v-2.0.2"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_go_annotation.csv","filename":"human_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Gene Ontology (GO) dataset contains human [taxid:9606] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"5c4f82735fedc1c864b49e41839d09d865e200f8fa54fd10802ebff6defca729","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_go_annotation.csv","filename":"human_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_go_annotation.stat.csv","filename":"human_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.082000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000223/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000223/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.951602","modified":"2022-09-26T09:04:47.947013","version":"v-2.1.1"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_go_annotation.csv","filename":"human_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Gene Ontology (GO) dataset contains human [taxid:9606] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"8b51f2e43cb22b83abb4b1d10fd65cf6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_go_annotation.csv","filename":"human_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_go_annotation.stat.csv","filename":"human_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:03.391000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000224/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000224/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b8abade0d4a0c16af3d1015bce8d0dcc60d73b03c4b3e5b301490098af4e4ce2","provenance_domain":{"name":"Rat Glycosylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.952590","modified":"2024-12-10T18:52:38.673Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycosylation Sites (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Rattus norvegicus proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":344,"last_update":"2024-12-10T18:52:38.673985Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000224/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000224/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.952590","modified":"2022-09-26T09:04:47.889690","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"bd9af1429c80314a6a698453441a3744936b88a82fa384392413e9e3ac09b094","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.327000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000224/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000224/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.952590","modified":"2022-09-26T09:04:47.889690","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"968bcb37eb4d841344a525e778b0fd5a","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:03.577000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000225/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000225/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"adf881e593ccf17794896f426e90d8dfeab85b5e5879795ac63a0af23f952212","provenance_domain":{"name":"Human Protein Glycosylation Diseases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.953629","modified":"2024-12-10T17:00:22.701Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Diseases dataset contains list of Homo sapiens [taxid:9606] diseases as described by OMIM and Monarch Initiative database. ","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship. ","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest. ","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, EMBL-EBI-UniProt and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the glycosylation disease information from the human_protein_disease_glyco.csv that is compiled from human_glyco-phenotype_disease_curation_list_v12-18-74.csv. The script maps the UniProtKB accessions to the UniprotKB canonical accessions. "}],"keywords":["disease","HPO","OMIM","Congenital Disorders of Glycosylation (CDG)","Monarch Initiative"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_glyco.csv","filename":"human_protein_disease_glyco.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_glyco.stat.csv","filename":"human_protein_disease_glyco.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases_Glyco","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":794,"last_update":"2024-12-10T17:00:22.701360Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000225/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000225/v-2.0.2","error_domain":{"empirical_error":{},"algorithmic_error":{}},"spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases_Glyco","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.953629","modified":"2022-09-26T09:04:47.911407","version":"v-2.0.2"},"description_domain":{"keywords":["disease","HPO","OMIM","Congenital Disorders of Glycosylation (CDG)","Monarch Initiative"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_protein_disease_glyco.csv","filename":"human_protein_disease_glyco.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_disease_glyco.csv","filename":"human_protein_disease_glyco.csv"}],"prerequisite":[],"description":"The script extracts the glycosylation disease information from the human_protein_disease_glyco.csv that is compiled from human_glyco-phenotype_disease_curation_list_v12-18-74.csv. The script maps the UniProtKB accessions to the UniprotKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Diseases dataset contains list of human [taxid:9606] diseases as described by OMIM and Monarch Initiative database. ","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship. ","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest. ","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, EMBL-EBI-UniProt and GlyGen. "],"etag":"c29436e38e7f2b6a9c414a68e45c4aa5ca3ff8a4475777665791f9131d677359","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_disease_glyco.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_disease_glyco.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_glyco.csv","filename":"human_protein_disease_glyco.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_glyco.stat.csv","filename":"human_protein_disease_glyco.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.938000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000225/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000225/v-2.1.1","error_domain":{"empirical_error":{},"algorithmic_error":{}},"spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases_Glyco","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.953629","modified":"2022-09-26T09:04:47.911407","version":"v-2.1.1"},"description_domain":{"keywords":["disease","HPO","OMIM","Congenital Disorders of Glycosylation (CDG)","Monarch Initiative"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/human_protein_disease_glyco.csv","filename":"human_protein_disease_glyco.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_disease_glyco.csv","filename":"human_protein_disease_glyco.csv"}],"prerequisite":[],"description":"The script extracts the glycosylation disease information from the human_protein_disease_glyco.csv that is compiled from human_glyco-phenotype_disease_curation_list_v12-18-74.csv. The script maps the UniProtKB accessions to the UniprotKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Diseases dataset contains list of human [taxid:9606] diseases as described by OMIM and Monarch Initiative database. ","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship. ","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest. ","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, EMBL-EBI-UniProt and GlyGen. "],"etag":"5cc7437b791b59be5554682f97b0665c","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_disease_glyco.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_disease_glyco.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_glyco.csv","filename":"human_protein_disease_glyco.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_glyco.stat.csv","filename":"human_protein_disease_glyco.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:03.783000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000226/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000226/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0c0a8512aba16ad09278fc1d89c26b0b21eb972478b098985e95b5f066f61a4c","provenance_domain":{"name":"Rat Glycosylation Sites (RCSB PDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.954510","modified":"2026-08-19T09:59:12.926Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycosylation Sites (RCSB PDB) dataset contains Rattus norvegicus [taxid:11106] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_pdb.stat.csv","filename":"rat_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":512,"last_update":"2026-08-19T09:59:12.926801Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000226/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000226/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (RCSB PDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.954510","modified":"2022-09-26T09:04:47.998388","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/N-linked-ARG-details","filename":"N-linked-ARG-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/N-linked-ASN-details","filename":"N-linked-ASN-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-ASP-details","filename":"O-linked-ASP-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-GLU-details","filename":"O-linked-GLU-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-SER-details","filename":"O-linked-SER-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-THR-details","filename":"O-linked-THR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/O-linked-TYR-details","filename":"O-linked-TYR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Glycosylation Sites (RCSB PDB) dataset contains rat [taxid:11106] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"etag":"e429f7566af12659254ed9e5166e7aa972f5a7aad916eea573dd16daf65d0493","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"N-linked-ARG-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.stat.csv","filename":"rat_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.510000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000226/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000226/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (RCSB PDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.954510","modified":"2022-09-26T09:04:47.998388","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/N-linked-ARG-details","filename":"N-linked-ARG-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/N-linked-ASN-details","filename":"N-linked-ASN-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-ASP-details","filename":"O-linked-ASP-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-GLU-details","filename":"O-linked-GLU-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-SER-details","filename":"O-linked-SER-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-THR-details","filename":"O-linked-THR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/O-linked-TYR-details","filename":"O-linked-TYR-details"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Glycosylation Sites (RCSB PDB) dataset contains rat [taxid:11106] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"etag":"f44e522f2305017951db880426d604e6","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"N-linked-ARG-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"/data/shared/glyds/downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.stat.csv","filename":"rat_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:03.983000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000227/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000227/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.955413","modified":"2024-06-03T20:48:37.666Z","version":"v-0.0.0"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref ChEMBL contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties. "],"etag":"18ad25cbb20bbfc32f48256bf0929e7331cd88767bbba51e958cc42fa4877c5d","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_chembl.csv","filename":"rat_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_chembl.stat.csv","filename":"rat_protein_xref_chembl.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2024-06-03T20:48:37.666264Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000227/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000227/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.955413","modified":"2022-09-26T09:04:48.033557","version":"v-2.0.2"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_chembl.csv","filename":"rat_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref ChEMBL contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties. "],"etag":"7215d26cbddee9f85017b91e1713492475abf31986abef3acf6ea0ea2b51106f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_chembl.csv","filename":"rat_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_chembl.stat.csv","filename":"rat_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.407000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000227/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000227/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.955413","modified":"2022-09-26T09:04:48.033557","version":"v-2.1.1"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_chembl.csv","filename":"rat_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref ChEMBL contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties. "],"etag":"d25e68939ce21fbb7b0bcce16972f145","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_chembl.csv","filename":"rat_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_chembl.stat.csv","filename":"rat_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:04.179000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000228/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000228/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-19T16:00:40.680035","modified":"2024-05-17T11:23:52.828Z","version":"v-0.0.0"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Signal Peptide dataset contains Homo sapiens [taxid:9606] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"500b3b08c560def04e1dea8f4eab6e0b1a82be61958806e84537e220cef0ee00","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_annotation.csv","filename":"human_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_peptidesequences.fasta","filename":"human_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_cleavedsequences.fasta","filename":"human_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_fullsequences.fasta","filename":"human_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_annotation.stat.csv","filename":"human_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_peptidesequences.stat.csv","filename":"human_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_cleavedsequences.stat.csv","filename":"human_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_signalp_fullsequences.stat.csv","filename":"human_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":683,"last_update":"2024-05-17T11:23:52.828499Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000228/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000228/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-19T16:00:40.680035","modified":"2022-09-26T09:04:47.894234","version":"v-2.0.2"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_signalp_annotation.csv","filename":"human_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_signalp_peptidesequences.fasta","filename":"human_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_signalp_cleavedsequences.fasta","filename":"human_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_signalp_fullsequences.fasta","filename":"human_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Signal Peptide dataset contains human [taxid:9606] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"34531f372589b8fe6923854b03c1f002c5da15ec6edd986b58452a10d6fef609","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_annotation.csv","filename":"human_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_peptidesequences.fasta","filename":"human_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_cleavedsequences.fasta","filename":"human_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_fullsequences.fasta","filename":"human_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_annotation.stat.csv","filename":"human_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_peptidesequences.stat.csv","filename":"human_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_cleavedsequences.stat.csv","filename":"human_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_signalp_fullsequences.stat.csv","filename":"human_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.708000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000228/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000228/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-19T16:00:40.680035","modified":"2022-09-26T09:04:47.894234","version":"v-2.1.1"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_signalp_annotation.csv","filename":"human_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_signalp_peptidesequences.fasta","filename":"human_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_signalp_cleavedsequences.fasta","filename":"human_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_signalp_fullsequences.fasta","filename":"human_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Signal Peptide dataset contains human [taxid:9606] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"2425e2c693c7a5604db9175621ac444d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_annotation.csv","filename":"human_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_peptidesequences.fasta","filename":"human_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_cleavedsequences.fasta","filename":"human_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_fullsequences.fasta","filename":"human_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_annotation.stat.csv","filename":"human_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_peptidesequences.stat.csv","filename":"human_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_cleavedsequences.stat.csv","filename":"human_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_signalp_fullsequences.stat.csv","filename":"human_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:04.385000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000229/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000229/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.957228","modified":"2024-05-17T11:23:52.869Z","version":"v-0.0.0"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref OMA contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes. "],"etag":"2fd632ca47346e2f971d206dcad39b3188145dd31455062b9c1cb03e8e825571","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_oma.stat.csv","filename":"rat_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":365,"last_update":"2024-05-17T11:23:52.869057Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000229/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000229/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.957228","modified":"2022-09-26T09:04:47.902537","version":"v-2.0.2"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref OMA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes. "],"etag":"582b2fafc77d6c5cd0a90ffe43df3bb3368d584a96e379bffb2f323fa2484dda","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_oma.stat.csv","filename":"rat_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.550000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000229/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000229/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OMA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.957228","modified":"2022-09-26T09:04:47.902537","version":"v-2.1.1"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref OMA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes. "],"etag":"b0eab339a014fb8f5c385208fbb41779","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oma.stat.csv","filename":"rat_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:04.594000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000230/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000230/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Congenital Disorders of Glycosylation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"},{"affiliation":"MGI","contribution":["authoredBy"],"name":"Cynthia Smith","email":"cynthia.Smith@jax.org"},{"affiliation":"MGI","contribution":[],"name":"Judith Blake","email":"judith.Blake@jax.org"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.958276","modified":"2024-05-17T11:23:52.908Z","version":"v-0.0.0"},"description_domain":{"keywords":["congenital disorders of glycosylation","MGI","Monarch Initiative","phenotype"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script maps the UniProtKB accessions to the UniProtKB Canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Congenital Disorders of Glycosylation dataset contains a list of congenital disorders of glycosylation mapped to human [taxid:9606] UniProtKB accessions. The dataset also contains mouse orthologs and links to phenotype page on MGI. If you use this dataset please provide proper attribution to Monarch Initiative and GlyGen. "],"etag":"8be5801029bf0a6c014600ada22e9b160d4b6abd0d9089259ff3961a3328813e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_cdg.csv","filename":"human_protein_disease_cdg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_cdg.stat.csv","filename":"human_protein_disease_cdg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":334,"last_update":"2024-05-17T11:23:52.908392Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000230/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000230/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Congenital Disorders of Glycosylation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"},{"affiliation":"MGI","contribution":["authoredBy"],"name":"Cynthia Smith","email":"cynthia.Smith@jax.org"},{"affiliation":"MGI","contribution":[],"name":"Judith Blake","email":"judith.Blake@jax.org"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.958276","modified":"2022-09-26T09:04:48.003973","version":"v-2.0.2"},"description_domain":{"keywords":["congenital disorders of glycosylation","MGI","Monarch Initiative","phenotype"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_disease_cdg.csv","filename":"human_protein_disease_cdg.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accessions to the UniProtKB Canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Congenital Disorders of Glycosylation dataset contains a list of congenital disorders of glycosylation mapped to human [taxid:9606] UniProtKB accessions. The dataset also contains mouse orthologs and links to phenotype page on MGI. If you use this dataset please provide proper attribution to Monarch Initiative and GlyGen. "],"etag":"226d5310decd6e2008136bda015537dfbc6fb6253bcdf18e52a5a00761bf989d","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_disease_cdg.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_disease_cdg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_cdg.csv","filename":"human_protein_disease_cdg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_cdg.stat.csv","filename":"human_protein_disease_cdg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.219000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000230/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000230/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Congenital Disorders of Glycosylation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"},{"affiliation":"MGI","contribution":["authoredBy"],"name":"Cynthia Smith","email":"cynthia.Smith@jax.org"},{"affiliation":"MGI","contribution":[],"name":"Judith Blake","email":"judith.Blake@jax.org"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.958276","modified":"2022-09-26T09:04:48.003973","version":"v-2.1.1"},"description_domain":{"keywords":["congenital disorders of glycosylation","MGI","Monarch Initiative","phenotype"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_disease_cdg.csv","filename":"human_protein_disease_cdg.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accessions to the UniProtKB Canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Congenital Disorders of Glycosylation dataset contains a list of congenital disorders of glycosylation mapped to human [taxid:9606] UniProtKB accessions. The dataset also contains mouse orthologs and links to phenotype page on MGI. If you use this dataset please provide proper attribution to Monarch Initiative and GlyGen. "],"etag":"6d047bdfb99fda4ccbed46b8518e90a9","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_disease_cdg.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_disease_cdg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_cdg.csv","filename":"human_protein_disease_cdg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_cdg.stat.csv","filename":"human_protein_disease_cdg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:04.802000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000231/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000231/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"36226b196f197b119b2f0ef989265cba3b92d62b55428a6980a88edc6ef7d791","provenance_domain":{"name":"Rat Phosphorylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.959200","modified":"2024-12-10T18:48:22.081Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Phosphorylation Sites (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from the UniProtKB Rattus norvegicus proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}],"keywords":["phosphorylation Sites","ptm processing","UniProtKB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":366,"last_update":"2024-12-10T18:48:22.081302Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000231/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000231/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.959200","modified":"2022-09-26T09:04:48.021609","version":"v-2.0.2"},"description_domain":{"keywords":["phosphorylation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Phosphorylation Sites (UniProtKB) dataset contains rat [taxid:10116] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"b4d28d27dc4fed99d921a24544d6e6646365285fabb484c50d4dca71506db6c6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.014000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000231/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000231/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.959200","modified":"2022-09-26T09:04:48.021609","version":"v-2.1.1"},"description_domain":{"keywords":["phosphorylation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Phosphorylation Sites (UniProtKB) dataset contains rat [taxid:10116] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"8989375a8696961b627dfb919bb2164f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:05.002000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000232/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000232/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.960116","modified":"2024-05-17T11:23:52.986Z","version":"v-0.0.0"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref CAZy contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates. "],"etag":"fe1ab5aa0558eed13b01c7e243dd2de9918a5be846ac3a3b0e1b4cc782a93ac1","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_cazy.csv","filename":"rat_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_cazy.stat.csv","filename":"rat_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":472,"last_update":"2024-05-17T11:23:52.986134Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000232/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000232/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.960116","modified":"2022-09-26T09:04:47.886795","version":"v-2.0.2"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_cazy.csv","filename":"rat_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref CAZy contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates. "],"etag":"2e21656ab58f2eedb48d4a56c01f977b44b99103fcaa917fd9064508fc9742b5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_cazy.csv","filename":"rat_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_cazy.stat.csv","filename":"rat_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.881000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000232/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000232/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CAZy","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.960116","modified":"2022-09-26T09:04:47.886795","version":"v-2.1.1"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_cazy.csv","filename":"rat_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref CAZy contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates. "],"etag":"1c4b05a71216e6512d266daaecc9a017","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_cazy.csv","filename":"rat_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_cazy.stat.csv","filename":"rat_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:05.195000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000233/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000233/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.961010","modified":"2024-05-17T11:23:53.028Z","version":"v-0.0.0"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse UniProtKB Xref IntAct dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"cdc546222d05cc6f808572c2943377d01363fbb020ccf074fb2cf8265e805ab2","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_intact.csv","filename":"mouse_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_intact.stat.csv","filename":"mouse_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":530,"last_update":"2024-05-17T11:23:53.028134Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000233/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000233/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.961010","modified":"2022-09-26T09:04:47.919039","version":"v-2.0.2"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_intact.csv","filename":"mouse_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse UniProtKB Xref IntAct dataset contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"ab3f655b1a3743d7d54c0263b0f20ab91b8d3b5a3db9b66a986f5f26a658f347","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_intact.csv","filename":"mouse_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_intact.stat.csv","filename":"mouse_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.316000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000233/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000233/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.961010","modified":"2022-09-26T09:04:47.919039","version":"v-2.1.1"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_intact.csv","filename":"mouse_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse UniProtKB Xref IntAct dataset contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"a29d76f9ec517c42d5d944f6db253a2a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_intact.csv","filename":"mouse_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_intact.stat.csv","filename":"mouse_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:05.395000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000234/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000234/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.961924","modified":"2024-05-17T11:23:53.066Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref CDD contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins. "],"etag":"bfbad0d8da891933653a7e045efc5f9194840133ec284003ddfd5522b305677b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_cdd.csv","filename":"rat_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_cdd.stat.csv","filename":"rat_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":427,"last_update":"2024-05-17T11:23:53.066746Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000234/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000234/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.961924","modified":"2022-09-26T09:04:47.933127","version":"v-2.0.2"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_cdd.csv","filename":"rat_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref CDD contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins. "],"etag":"d88b256993c29f22f201a30d8ba9dd6c979df73dbb1cc16ebf2e2c12783724ec","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_cdd.csv","filename":"rat_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_cdd.stat.csv","filename":"rat_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.978000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000234/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000234/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CDD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.961924","modified":"2022-09-26T09:04:47.933127","version":"v-2.1.1"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_cdd.csv","filename":"rat_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref CDD contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins. "],"etag":"be67894addaecec93337891e1d9ebe13","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_cdd.csv","filename":"rat_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_cdd.stat.csv","filename":"rat_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:05.594000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000235/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000235/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.962804","modified":"2024-05-17T11:23:53.104Z","version":"v-0.0.0"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Citations (RefSeq) datasets contains Mus musculus [taxid:10090] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions).  If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"ecbf19cf4afa03f0fe815e42e48672a813534359b63c85800481c11e810067f2","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_citations_refseq.stat.csv","filename":"mouse_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":315,"last_update":"2024-05-17T11:23:53.104758Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000235/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000235/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-09-06T14:06:38.962804","modified":"2022-09-26T09:04:47.954130","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Citations (RefSeq) datasets contains mouse [taxid:10090] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"1c85321e59d9e3b024c9b577ee53feb1e29bbeb6aba114916a3541234843dcc4","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_function_refseq.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_refseq.stat.csv","filename":"mouse_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.126000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000235/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000235/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.962804","modified":"2022-09-26T09:04:47.954130","version":"v-2.1.1"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Citations (RefSeq) datasets contains mouse [taxid:10090] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"886990f77a5c4e0e76c81cc058eb664f","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_function_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_refseq.stat.csv","filename":"mouse_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:05.793000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000236/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000236/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.963796","modified":"2024-05-17T11:23:53.143Z","version":"v-0.0.0"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human UniProtKB Xref IntAct dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"54311ec79b24f2084a1a728e6ce302dbf88697bfbbf6aebdbcb4271bf2d1dd2e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_intact.csv","filename":"human_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_intact.stat.csv","filename":"human_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":529,"last_update":"2024-05-17T11:23:53.143698Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000236/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000236/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.963796","modified":"2022-09-26T09:04:47.983810","version":"v-2.0.2"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_intact.csv","filename":"human_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human UniProtKB Xref IntAct dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"4e59e2799f5dfe1171dff5503e3b47eeec62f5761ba2db62e7de0ecc01caf2a2","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_intact.csv","filename":"human_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_intact.stat.csv","filename":"human_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.322000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000236/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000236/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.963796","modified":"2022-09-26T09:04:47.983810","version":"v-2.1.1"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_intact.csv","filename":"human_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human UniProtKB Xref IntAct dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"7d48b0c12741c6ebba88edf4a4fb216d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_intact.csv","filename":"human_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_intact.stat.csv","filename":"human_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:05.988000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000237/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000237/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dbcbe969480aaae01d6d7920890a04521cd30fafc137e2798a1f6f17431bcc19","provenance_domain":{"name":"Rat Transcript Locus (Ensembl Transcript coordinates)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.964793","modified":"2024-12-10T14:43:22.215Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Ensembl Transcript Locus (Transcript coordinates)s contains UniProtKB Rattus norvegicus [taxid:10116] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end positions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}],"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_transcriptlocus.csv","filename":"rat_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_transcriptlocus.stat.csv","filename":"rat_protein_transcriptlocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":475,"last_update":"2024-12-10T14:43:22.215018Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000237/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000237/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.964793","modified":"2022-09-26T09:04:47.985614","version":"v-2.0.2"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_idmapping.csv","filename":"rat_protein_idmapping.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt","filename":"uniprot-proteome-10116-rattus-norvegicus-2019-05.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_transcriptlocus.csv","filename":"rat_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Ensembl Transcript Locus (Transcript coordinates)s contains UniProtKB rat [taxid:10116] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end positions. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"5ba90f254570f0e23a60a3af06abba5900a8e4d604672a12ec0f29da47301ce6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_transcriptlocus.csv","filename":"rat_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_transcriptlocus.stat.csv","filename":"rat_protein_transcriptlocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.832000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000237/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000237/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.964793","modified":"2022-09-26T09:04:47.985614","version":"v-2.1.1"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_idmapping.csv","filename":"rat_protein_idmapping.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt","filename":"uniprot-proteome-10116-rattus-norvegicus-2019-05.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_transcriptlocus.csv","filename":"rat_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Ensembl Transcript Locus (Transcript coordinates)s contains UniProtKB rat [taxid:10116] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end positions. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"2a040882529e508ecfb5651592be355b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_transcriptlocus.csv","filename":"rat_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_transcriptlocus.stat.csv","filename":"rat_protein_transcriptlocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:06.180000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000238/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000238/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.965792","modified":"2024-06-03T20:49:33.358Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref NCBI Gene dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide. "],"etag":"7f4acae9d3a3f510b85d4f719db3d5924502612effe78a572820f74f17834d54","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_geneid.stat.csv","filename":"rat_protein_xref_geneid.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2024-06-03T20:49:33.358181Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000238/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000238/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.965792","modified":"2022-09-26T09:04:47.920655","version":"v-2.0.2"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref NCBI Gene dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide. "],"etag":"ba2b0c79f46657faaf36215dc9839094ba631bd2e8fb08ba524ab28afe281033","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_geneid.stat.csv","filename":"rat_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.139000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000238/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000238/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.965792","modified":"2022-09-26T09:04:47.920655","version":"v-2.1.1"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref NCBI Gene dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide. "],"etag":"d526869d0f7f068304e1428e4a8c1f6c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_geneid.stat.csv","filename":"rat_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:06.375000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000239/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000239/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.966707","modified":"2024-06-03T20:35:47.933Z","version":"v-0.0.0"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Homo sapiens [taxid:9606] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"etag":"7cea48f2289696c6235b3b562359839058616dd5474958e90275bc107565f534","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycosylation_motifs.csv","filename":"human_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycosylation_motifs.stat.csv","filename":"human_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2024-06-03T20:35:47.933305Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000239/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000239/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.966707","modified":"2022-09-26T09:04:47.966596","version":"v-2.0.2"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_glycosylation_motifs.csv","filename":"human_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for human [taxid:9606] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"etag":"46924d0d6ccb43caa2fcab0d1de386be736866949c3a905798bceee8cac30b93","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycosylation_motifs.csv","filename":"human_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycosylation_motifs.stat.csv","filename":"human_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:53.878000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000239/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000239/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.966707","modified":"2022-09-26T09:04:47.966596","version":"v-2.1.1"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_glycosylation_motifs.csv","filename":"human_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for human [taxid:9606] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"etag":"165d1f49e69a09835a6d1618a62b0d89","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycosylation_motifs.csv","filename":"human_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycosylation_motifs.stat.csv","filename":"human_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:06.575000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000240/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000240/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.967574","modified":"2024-06-03T20:27:27.040Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all rat canonical accessions data from the triplestore containing triples from nt file and extracts  dataset in a fasta format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Canonical Sequences (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"523cf174307826a8a6670fc00a6b549bd0eb7ac9ad7ea56872a768645cca15e6","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_canonicalsequences.stat.csv","filename":"rat_protein_canonicalsequences.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":252,"last_update":"2024-06-03T20:27:27.040309Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000240/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000240/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.967574","modified":"2022-09-26T09:04:47.996653","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all rat canonical accessions data from the triplestore containing triples from nt file and extracts  dataset in a fasta format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Canonical Sequences (UniProtKB) dataset contains rat [taxid:10116] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"c9d1279058589365fa441197ca78c44806cf481fb30a06f9feb3b0eaa8143027","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_canonicalsequences.stat.csv","filename":"rat_protein_canonicalsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.908000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000240/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000240/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.967574","modified":"2022-09-26T09:04:47.996653","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all rat canonical accessions data from the triplestore containing triples from nt file and extracts  dataset in a fasta format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Canonical Sequences (UniProtKB) dataset contains rat [taxid:10116] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"65b4eedcb0a1724fb333f72b69403a2e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_canonicalsequences.stat.csv","filename":"rat_protein_canonicalsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:06.769000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000241/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000241/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.968442","modified":"2024-05-17T11:23:53.336Z","version":"v-0.0.0"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Information dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"1d98ee7319a069ba77677fc6783fed4a5fbc4735c5026bce6469ca176de0f117","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_info_uniprotkb.csv","filename":"rat_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_info_uniprotkb.stat.csv","filename":"rat_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":286,"last_update":"2024-05-17T11:23:53.336799Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000241/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000241/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.968442","modified":"2022-09-26T09:04:47.969437","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_info_uniprotkb.csv","filename":"rat_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Information dataset contains rat [taxid:10116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"4577b23c005db8dae0bfd22ec5ce0aa73905113c3b92af4c38c7d95497a1f424","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_info_uniprotkb.csv","filename":"rat_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_info_uniprotkb.stat.csv","filename":"rat_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.045000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000241/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000241/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.968442","modified":"2022-09-26T09:04:47.969437","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_info_uniprotkb.csv","filename":"rat_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Information dataset contains rat [taxid:10116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"0d8e56d22a53a6dca710ef16d593ae3e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_info_uniprotkb.csv","filename":"rat_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_info_uniprotkb.stat.csv","filename":"rat_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:06.967000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000242/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000242/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.969307","modified":"2024-05-17T11:23:53.377Z","version":"v-0.0.0"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Gene Ontology (GO) dataset contains Rattus norvegicus [taxid:10116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"a40de91c5cf61d0066fc6677e1a5ce91b8d0e536e675afe9dd163f0c38c9dea5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_go_annotation.csv","filename":"rat_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_go_annotation.stat.csv","filename":"rat_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":267,"last_update":"2024-05-17T11:23:53.377652Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000242/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000242/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.969307","modified":"2022-09-26T09:04:47.956734","version":"v-2.0.2"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_go_annotation.csv","filename":"rat_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Gene Ontology (GO) dataset contains rat [taxid:10116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"77c49eddba48773fff9f8817f4a31d05e2a66e3d656359a57077454114fecd61","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_go_annotation.csv","filename":"rat_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_go_annotation.stat.csv","filename":"rat_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:15.324000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000242/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000242/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.969307","modified":"2022-09-26T09:04:47.956734","version":"v-2.1.1"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_go_annotation.csv","filename":"rat_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Gene Ontology (GO) dataset contains rat [taxid:10116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"6c59813c3023f8be504738fd8ef7a390","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_go_annotation.csv","filename":"rat_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_go_annotation.stat.csv","filename":"rat_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:07.159000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000243/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000243/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.970158","modified":"2024-05-17T11:23:53.418Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref InterPro contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterize them. "],"etag":"9e056b9ebbf541db2adb2e18d41e7440c6791d1531da7d2e2ffee9ed244f1e6e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_interpro.csv","filename":"rat_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_interpro.stat.csv","filename":"rat_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":471,"last_update":"2024-05-17T11:23:53.418509Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000243/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000243/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.970158","modified":"2022-09-26T09:04:47.930942","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlistcsv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_interpro.csv","filename":"rat_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref InterPro contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterize them. "],"etag":"6a6145fcb151333b1efc6569c862ff9b230a26ec91d26fca1aed6db121720893","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_interpro.csv","filename":"rat_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_interpro.stat.csv","filename":"rat_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:53.054000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000243/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000243/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.970158","modified":"2022-09-26T09:04:47.930942","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlistcsv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_interpro.csv","filename":"rat_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref InterPro contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterize them. "],"etag":"88cde05ae78ca78c2bfd0af3b85683b6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_interpro.csv","filename":"rat_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_interpro.stat.csv","filename":"rat_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:07.361000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000244/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000244/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.971023","modified":"2024-05-17T11:23:53.459Z","version":"v-0.0.0"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Proteome Master list dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"7ac87cef737c89532a9c28925ff493c33ad6a1ef7b929fde042201f079c253de","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_masterlist.stat.csv","filename":"rat_protein_masterlist.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":298,"last_update":"2024-05-17T11:23:53.459473Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000244/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000244/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.971023","modified":"2022-09-26T09:04:47.899178","version":"v-2.0.2"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Proteome Master list dataset contains rat [taxid:10116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"9875a7389958d17e6d4b157a5e4f5014f8ac022e1e84b7eb3113464483e9ee41","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.stat.csv","filename":"rat_protein_masterlist.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.907000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000244/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000244/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.971023","modified":"2022-09-26T09:04:47.899178","version":"v-2.1.1"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Proteome Master list dataset contains rat [taxid:10116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"c5e4eacc3c3bc8151e9722576b576b65","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.stat.csv","filename":"rat_protein_masterlist.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:07.546000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000245/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000245/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.971888","modified":"2024-05-17T11:23:53.498Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref PDB contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"17dacc4dc2272ab314c948431ce370bc3faaf3062c20201276160c57a6d6d5b0","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_pdb.csv","filename":"rat_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_pdb.stat.csv","filename":"rat_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":393,"last_update":"2024-05-17T11:23:53.498305Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000245/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000245/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.971888","modified":"2022-09-26T09:04:47.896933","version":"v-2.0.2"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_pdb.csv","filename":"rat_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref PDB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"c0eaf3fcd7a5e2a804bbfba2f07059a08936caa3c95a08b728aa898de2accdca","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_pdb.csv","filename":"rat_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_pdb.stat.csv","filename":"rat_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.273000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000245/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000245/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.971888","modified":"2022-09-26T09:04:47.896933","version":"v-2.1.1"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_pdb.csv","filename":"rat_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref PDB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"etag":"5ea4249de913084c28f3629163bb10de","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pdb.csv","filename":"rat_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pdb.stat.csv","filename":"rat_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:07.740000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000247/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000247/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.973677","modified":"2024-06-03T20:50:11.762Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Function (UniProtKB) dataset contains biological functional annotations for Rattus norvegicus [taxid:10116] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"0647f4f37920f6344e20224d1ec40f0f2273cf355d6c9e40247d683da3dceeb5","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_function_uniprotkb.csv","filename":"rat_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_function_uniprotkb.stat.csv","filename":"rat_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":264,"last_update":"2024-06-03T20:50:11.762366Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000247/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000247/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.973677","modified":"2022-09-26T09:04:48.006389","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_function_uniprotkb.csv","filename":"rat_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Function (UniProtKB) dataset contains biological functional annotations for rat [taxid:10116] protein accessions from the UniProtKB database. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"448dbef790f52b350f5e9a1b9b6d8bb2ed38d5fba4dcae7d4724fa8e0af6d116","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_function_uniprotkb.csv","filename":"rat_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_function_uniprotkb.stat.csv","filename":"rat_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.322000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000247/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000247/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.973677","modified":"2022-09-26T09:04:48.006389","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_function_uniprotkb.csv","filename":"rat_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Function (UniProtKB) dataset contains biological functional annotations for rat [taxid:10116] protein accessions from the UniProtKB database. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"2468287e88886a834cdce583fe96e91d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_function_uniprotkb.csv","filename":"rat_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_function_uniprotkb.stat.csv","filename":"rat_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:07.937000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000248/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000248/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.974540","modified":"2024-06-03T20:50:31.568Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Pfam contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"9196f039da929e0193069950a85ceb245fc3eb445a7247235945d43f5fb3c534","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_pfam.csv","filename":"rat_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_pfam.stat.csv","filename":"rat_protein_xref_pfam.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":392,"last_update":"2024-06-03T20:50:31.568140Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000248/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000248/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.974540","modified":"2022-09-26T09:04:47.909528","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_maserlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_pfam.csv","filename":"rat_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Pfam contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"887802582048743043bd67b1d8638004b604a2dcf752739ad99d3937b40c3d70","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_pfam.csv","filename":"rat_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_pfam.stat.csv","filename":"rat_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.813000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000248/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000248/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.974540","modified":"2022-09-26T09:04:47.909528","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_maserlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_pfam.csv","filename":"rat_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Pfam contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"2934463f30dd221d91db270aba0b8d57","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pfam.csv","filename":"rat_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pfam.stat.csv","filename":"rat_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:08.129000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000249/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000249/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.975527","modified":"2024-05-17T11:23:53.614Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Function (NCBI RefSeq) dataset contains biological function annotation of Rattus norvegicus [taxid:10116] genes from GeneRIF section in the NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"7368b55dd113d7e6db9a703514fa8ba2551a419910eeadc1a53227424626c061","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_function_refseq.csv","filename":"rat_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_function_refseq.stat.csv","filename":"rat_protein_function_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":263,"last_update":"2024-05-17T11:23:53.614632Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000249/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000249/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-09-06T14:06:38.975527","modified":"2022-09-26T09:04:47.890686","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Function (NCBI RefSeq) dataset contains biological function annotation of rat [taxid:10116] genes from GeneRIF section in the NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"a00147d6cf413fc89b75f9cc5b81e4d9d91b3cc33e7a869e198a75763cc32dec","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10116.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_10116.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_function_refseq.csv","filename":"rat_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_function_refseq.stat.csv","filename":"rat_protein_function_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.013000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000249/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000249/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.975527","modified":"2022-09-26T09:04:47.890686","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Function (NCBI RefSeq) dataset contains biological function annotation of rat [taxid:10116] genes from GeneRIF section in the NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"c2dd53b7145798f08c97994db9928df0","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10116.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_10116.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_function_refseq.csv","filename":"rat_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_function_refseq.stat.csv","filename":"rat_protein_function_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:08.316000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000250/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000250/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.976805","modified":"2024-05-17T11:23:53.653Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref KEGG PATHWAY contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks. "],"etag":"e903c12b2f271d8b2198a271ca8372a1d31aa2e5b81df71d7b5a78931a31a120","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_kegg.csv","filename":"rat_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_kegg.stat.csv","filename":"rat_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":415,"last_update":"2024-05-17T11:23:53.653768Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000250/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000250/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.976805","modified":"2022-09-26T09:04:48.019370","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_kegg.csv","filename":"rat_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref KEGG PATHWAY contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks. "],"etag":"9f0167fd92115472fae75200d985019137a550eb744aa57243e1aea383d70e91","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_kegg.csv","filename":"rat_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_kegg.stat.csv","filename":"rat_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.417000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000250/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000250/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref KEGG PATHWAY","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.976805","modified":"2022-09-26T09:04:48.019370","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_kegg.csv","filename":"rat_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref KEGG PATHWAY contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks. "],"etag":"b406b5d7029e9901ed408488d840815a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_kegg.csv","filename":"rat_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_kegg.stat.csv","filename":"rat_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:08.506000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000251/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000251/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a200da4731fbed85775e504d333d89f3e6732aeadff1b3fb2ec65a8fb8bf153f","provenance_domain":{"name":"Rat Proteoform Citations (UniCarbKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.978102","modified":"2024-12-10T18:47:54.650Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Proteoform Citations (UniCarbKB) contains Rattus norvegicus [taxid:10116] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}],"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":627,"last_update":"2024-12-10T18:47:54.649995Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000251/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000251/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteoform Citations (UniCarbKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-09-06T14:06:38.978102","modified":"2022-09-26T09:04:48.008169","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_citations_unicarbkb.csv","filename":"rat_proteoform_citations_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Proteoform Citations (UniCarbKB) contains rat [taxid:10116] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"etag":"bdf243b9517ae4fcf3d6a6abd7bca79aa4965867b13becddaa15793cb0c835a3","io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/doi_citations.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_unicarbkb.csv","filename":"rat_proteoform_citations_glycosylation_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_unicarbkb.stat.csv","filename":"rat_proteoform_citations_glycosylation_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.865000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000251/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000251/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3ce5052ed004f8a338e311fddedbe823","provenance_domain":{"name":"Rat Proteoform Citations (UniCarbKB)","version":"v-2.1.1","created":"2019-09-06T14:06:38.978102","modified":"2023-03-14T16:34:23.531Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat Proteoform Citations (UniCarbKB) contains rat [taxid:10116] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. "],"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_citations_sites_glycosylation_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/doi_citations.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:08.720000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000252/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000252/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.979310","modified":"2024-05-17T11:23:53.733Z","version":"v-0.0.0"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Gene Ontology (GO) dataset contains Mus musculus [taxid:10090] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"019024f148f284f53fe20c53f01e1797183bf4a298c61aba2b7d2f40025aba51","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_go_annotation.csv","filename":"mouse_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_go_annotation.stat.csv","filename":"mouse_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":264,"last_update":"2024-05-17T11:23:53.733626Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000252/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000252/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.979310","modified":"2022-09-26T09:04:47.900986","version":"v-2.0.2"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_go_annotation.csv","filename":"mouse_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Gene Ontology (GO) dataset contains mouse [taxid:10090] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"a4381da3021213c29f12182ad70aafec40d2059d08b2979f993750db8ef14815","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_go_annotation.csv","filename":"mouse_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_go_annotation.stat.csv","filename":"mouse_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.809000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000252/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000252/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.979310","modified":"2022-09-26T09:04:47.900986","version":"v-2.1.1"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_go_annotation.csv","filename":"mouse_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Gene Ontology (GO) dataset contains mouse [taxid:10090] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"8bd00391f7c0d73cb26a97a808ef874b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_go_annotation.csv","filename":"mouse_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_go_annotation.stat.csv","filename":"mouse_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:08.923000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000253/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000253/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.980261","modified":"2024-05-17T11:23:53.776Z","version":"v-0.0.0"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Citations dataset contains publication information for Rattus norvegicus [taxid:10116] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"8d86ed103956cff15500c04fd5768368a39e795ccd9754009144e0ac2b7a84d9","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_citations_uniprotkb.stat.csv","filename":"rat_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2024-05-17T11:23:53.776158Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000253/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000253/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.980261","modified":"2022-09-26T09:04:47.895366","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv","filename":"rat_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Citations dataset contains publication information for rat [taxid:10116] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"4b65a6a35e11254aa9524e49e518cd638aeeebc9572e4c47dcfb0d082e97b7b0","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_uniprotkb.stat.csv","filename":"rat_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.789000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000253/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000253/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.980261","modified":"2022-09-26T09:04:47.895366","version":"v-2.1.1"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv","filename":"rat_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Citations dataset contains publication information for rat [taxid:10116] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"65dff38fc18840783df43a0c13bd1e1c","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_uniprotkb.stat.csv","filename":"rat_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:09.111000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000254/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000254/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.981217","modified":"2024-05-17T11:23:53.819Z","version":"v-0.0.0"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Phosphorylation Sites (UniProtKB) dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"d3383c20a1dc27aed602f2130e1ac1d7b57a9da82f18e6f1453b68327a064a5d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-05-17T11:23:53.819976Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000254/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000254/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.981217","modified":"2022-09-26T09:04:47.959542","version":"v-2.0.2"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Phosphorylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"8e3ce6f577be66eb3c6c53d682a3a0c844f2d563cd5f1fe2c95177282c534b32","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.580000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000254/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000254/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.981217","modified":"2022-09-26T09:04:47.959542","version":"v-2.1.1"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Phosphorylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"c167ae4d36f9302e0776c6e57e0576e7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:09.304000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000255/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000255/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.982193","modified":"2024-05-17T11:23:53.859Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB","protein alternative name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Isoform sequences (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] protein fasta sequences for the rat isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"df35807c039399e716313915549ec639c0482b155c994c9d939889098bc6bd2d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_allsequences.stat.csv","filename":"rat_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":271,"last_update":"2024-05-17T11:23:53.859002Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000255/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000255/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.982193","modified":"2022-09-26T09:04:47.928716","version":"v-2.0.2"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB","protein alternative name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt","filename":"uniprot-proteome-10116-rattus-norvegicus-2019-05.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Isoform sequences (UniProtKB) dataset contains rat [taxid:10116] protein fasta sequences for the rat isoform accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"25f2d3dea9f76f36a9970baae29c76495929af5ef4d2d252cd918b0c02eb2312","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_allsequences.stat.csv","filename":"rat_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.164000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000255/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000255/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.982193","modified":"2022-09-26T09:04:47.928716","version":"v-2.1.1"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB","protein alternative name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt","filename":"uniprot-proteome-10116-rattus-norvegicus-2019-05.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Isoform sequences (UniProtKB) dataset contains rat [taxid:10116] protein fasta sequences for the rat isoform accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"e340255f786894330d5459d9878ac9a7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_allsequences.stat.csv","filename":"rat_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:09.491000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000256/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000256/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.983152","modified":"2024-05-17T11:23:53.899Z","version":"v-0.0.0"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Citations (RefSeq) datasets contains Homo sapiens [taxid:9606] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"f66f298e9ef98bfd4313f457cdcc9cf3d0e6622c2e031dc865d3c314e9e609a7","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_refseq.stat.csv","filename":"human_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-05-17T11:23:53.899602Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000256/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000256/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-09-06T14:06:38.983152","modified":"2022-09-26T09:04:47.995186","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Citations (RefSeq) datasets contains human [taxid:9606] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"09cba33c4ce49723f1df4d7f259901b148060f6aea58c712165391eecd4dd8de","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"human_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_function_refseq.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_refseq.stat.csv","filename":"human_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.183000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000256/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000256/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.983152","modified":"2022-09-26T09:04:47.995186","version":"v-2.1.1"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Citations (RefSeq) datasets contains human [taxid:9606] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"etag":"82c378e32bee580953196d94c2c7cf9c","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"human_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_function_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_refseq.stat.csv","filename":"human_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:09.685000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000257/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000257/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.984081","modified":"2024-05-17T11:23:53.937Z","version":"v-0.0.0"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref OrthoDB contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology. "],"etag":"e4e667f78e97d3fdf11dbf9a2f4cc298b47248187c7863e4e2f7ffeed95d8768","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_orthodb.csv","filename":"rat_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_orthodb.stat.csv","filename":"rat_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":430,"last_update":"2024-05-17T11:23:53.937583Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000257/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000257/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.984081","modified":"2022-09-26T09:04:47.971474","version":"v-2.0.2"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_orthodb.csv","filename":"rat_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref OrthoDB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology. "],"etag":"a28b478c12d344700b74ed467a1cabeee373ea266cbe5fe56fb21c4cc86b1874","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_orthodb.csv","filename":"rat_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_orthodb.stat.csv","filename":"rat_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.095000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000257/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000257/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OrthoDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.984081","modified":"2022-09-26T09:04:47.971474","version":"v-2.1.1"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_orthodb.csv","filename":"rat_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref OrthoDB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology. "],"etag":"dc73b4370e8ea28f4fc16d7f717bfd90","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_orthodb.csv","filename":"rat_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_orthodb.stat.csv","filename":"rat_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:09.876000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000258/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000258/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1711a56feb0d03116e9582f2a829e3b5ee3be42c8799f03e47d948878628beef","provenance_domain":{"name":"Homolog Clusters","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.985197","modified":"2025-03-05T15:54:11.343Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Homolog Clusters dataset contains homologs of organisms present in GlyGen mapped to UniProtKB canonical accessions. The homologs data is downloaded from OMA browser and the Alliance of Genome Resources (AGR). If you use this dataset please provide proper attribution to OMA Browser, AGR, and GlyGen. "],"description_domain":{"keywords":["homologs","orthologs","AGR","OMA"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the GlyGen species homolog data from the input files and using xref files, maps the identifiers to UniProtKB canonical accessions. "}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_homolog_clusters.csv","filename":"protein_homolog_clusters.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_homolog_clusters.stat.csv","filename":"protein_homolog_clusters.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae S288C"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepatitis C virus (isolate Japanese)"},{"category_name":"species","category_value":"Danio rerio"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Homologs","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":369,"last_update":"2025-03-05T15:54:11.343481Z","access_count":11},{"object_id":"https://biocomputeobject.org/GLY_000258/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000258/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Homologs","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Homolog Clusters","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2019-09-06T14:06:38.985197","modified":"2022-09-26T09:04:47.943513","version":"v-2.0.2"},"description_domain":{"keywords":["homologs","orthologs","MGI","OMA"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"mouse_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/mgi_homologs.csv","filename":"mgi_homologs.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"mouse_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/rat_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"rat_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/homolog_clusters.csv","filename":"homolog_clusters.csv"}],"prerequisite":[],"description":"The script extracts the human, mouse and rat homologs from the input files and using xref files, maps the identifiers to UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"usability_domain":["The Homolog Clusters dataset contains homologs of human [taxid: 9606], mouse [taxid:10090] and rat [taxid:10116] species mapped to UniProtKB canonical accessions. The homologs data is downloaded from OMA browser and MGI. If you use this dataset please provide proper attribution to MGI, OMA Browser and GlyGen. "],"etag":"eede5bceb3a16be8a4c2301c415aba1679eae737b013084f68d6626cf3c750b4","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_homolog_clusters.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/protein_homolog_clusters.csv"}},{"uri":{"filename":"fruitfly_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_transcriptlocus.csv"}},{"uri":{"filename":"fruitfly_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_geneid.csv"}},{"uri":{"filename":"fruitfly_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_oma.csv"}},{"uri":{"filename":"human_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_transcriptlocus.csv"}},{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"human_protein_xref_hgnc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_hgnc.csv"}},{"uri":{"filename":"human_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_oma.csv"}},{"uri":{"filename":"mouse_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_transcriptlocus.csv"}},{"uri":{"filename":"mouse_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_geneid.csv"}},{"uri":{"filename":"mouse_protein_xref_mgi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_mgi.csv"}},{"uri":{"filename":"mouse_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_oma.csv"}},{"uri":{"filename":"rat_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_transcriptlocus.csv"}},{"uri":{"filename":"rat_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_geneid.csv"}},{"uri":{"filename":"rat_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_oma.csv"}},{"uri":{"filename":"sarscov1_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_geneid.csv"}},{"uri":{"filename":"sarscov2_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_geneid.csv"}},{"uri":{"filename":"mgi_homologs.csv","uri":"https:/data.glygen.org/ln2downloads/mgi/2022_07_07/mgi_homologs.csv"}},{"uri":{"filename":"fruitfly_human_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/fruitfly_human_oma_orthologs_july2022.csv"}},{"uri":{"filename":"fruitfly_mouse_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/fruitfly_mouse_oma_orthologs_july2022.csv"}},{"uri":{"filename":"fruitfly_rat_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/fruitfly_rat_oma_orthologs_july2022.csv"}},{"uri":{"filename":"human_fruitfly_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/human_fruitfly_oma_orthologs_july2022.csv"}},{"uri":{"filename":"human_mouse_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/human_mouse_oma_orthologs_july2022.csv"}},{"uri":{"filename":"human_rat_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/human_rat_oma_orthologs_july2022.csv"}},{"uri":{"filename":"mouse_fruitfly_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/mouse_fruitfly_oma_orthologs_july2022.csv"}},{"uri":{"filename":"mouse_human_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/mouse_human_oma_orthologs_july2022.csv"}},{"uri":{"filename":"mouse_rat_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/mouse_rat_oma_orthologs_july2022.csv"}},{"uri":{"filename":"rat_fruitfly_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/rat_fruitfly_oma_orthologs_july2022.csv"}},{"uri":{"filename":"rat_human_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/rat_human_oma_orthologs_july2022.csv"}},{"uri":{"filename":"rat_mouse_oma_orthologs_july2022.csv","uri":"https:/data.glygen.org/ln2downloads/oma/2022_07_07/rat_mouse_oma_orthologs_july2022.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_homolog_clusters.csv","filename":"protein_homolog_clusters.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_homolog_clusters.stat.csv","filename":"protein_homolog_clusters.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.313000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000258/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000258/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"Homologs","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (genotype 1a, isolate H)"},{"category_name":"species","category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)"},{"category_name":"species","category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Homolog Clusters","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.985197","modified":"2023-09-11T23:00:35","version":"v-2.1.1"},"description_domain":{"keywords":["homologs","orthologs","MGI","OMA"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"mouse_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/mgi_homologs.csv","filename":"mgi_homologs.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"mouse_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/rat_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"rat_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/homolog_clusters.csv","filename":"homolog_clusters.csv"}],"prerequisite":[],"description":"The script extracts the human, mouse and rat homologs from the input files and using xref files, maps the identifiers to UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"usability_domain":["The Homolog Clusters dataset contains homologs of human [taxid: 9606], mouse [taxid:10090] and rat [taxid:10116] species mapped to UniProtKB canonical accessions. The homologs data is downloaded from OMA browser and MGI. If you use this dataset please provide proper attribution to MGI, OMA Browser and GlyGen. "],"etag":"48ce7dcb467bb40ee950c762a75d65065716da18","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_homolog_clusters.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/protein_homolog_clusters.csv"}},{"uri":{"filename":"fruitfly_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_transcriptlocus.csv"}},{"uri":{"filename":"fruitfly_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_geneid.csv"}},{"uri":{"filename":"fruitfly_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oma.csv"}},{"uri":{"filename":"human_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_transcriptlocus.csv"}},{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"human_protein_xref_hgnc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.csv"}},{"uri":{"filename":"human_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oma.csv"}},{"uri":{"filename":"mouse_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_transcriptlocus.csv"}},{"uri":{"filename":"mouse_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv"}},{"uri":{"filename":"mouse_protein_xref_mgi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_mgi.csv"}},{"uri":{"filename":"mouse_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oma.csv"}},{"uri":{"filename":"rat_protein_transcriptlocus.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_transcriptlocus.csv"}},{"uri":{"filename":"rat_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_geneid.csv"}},{"uri":{"filename":"rat_protein_xref_oma.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oma.csv"}},{"uri":{"filename":"sarscov1_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_geneid.csv"}},{"uri":{"filename":"sarscov2_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_geneid.csv"}},{"uri":{"filename":"mgi_homologs.tsv","uri":"/data/shared/glyds/downloads/mgi/2023_04/mgi_homologs.tsv"}},{"uri":{"filename":"fruitfly_human_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/fruitfly_human_oma_orthologs.txt"}},{"uri":{"filename":"fruitfly_mouse_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/fruitfly_mouse_oma_orthologs.txt"}},{"uri":{"filename":"fruitfly_rat_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/fruitfly_rat_oma_orthologs.txt"}},{"uri":{"filename":"human_fruitfly_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/human_fruitfly_oma_orthologs.txt"}},{"uri":{"filename":"human_mouse_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/human_mouse_oma_orthologs.txt"}},{"uri":{"filename":"human_rat_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/human_rat_oma_orthologs.txt"}},{"uri":{"filename":"mouse_fruitfly_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/mouse_fruitfly_oma_orthologs.txt"}},{"uri":{"filename":"mouse_human_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/mouse_human_oma_orthologs.txt"}},{"uri":{"filename":"mouse_rat_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/mouse_rat_oma_orthologs.txt"}},{"uri":{"filename":"rat_fruitfly_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/rat_fruitfly_oma_orthologs.txt"}},{"uri":{"filename":"rat_human_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/rat_human_oma_orthologs.txt"}},{"uri":{"filename":"rat_mouse_oma_orthologs.txt","uri":"/data/shared/glyds/downloads/oma/2023_05_23/rat_mouse_oma_orthologs.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_homolog_clusters.csv","filename":"protein_homolog_clusters.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_homolog_clusters.stat.csv","filename":"protein_homolog_clusters.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-09-11T23:00:41.659000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000259/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000259/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.986196","modified":"2024-05-17T11:23:54.015Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref UniCarbKB contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"etag":"76bf9db0138f4d09be6a2637487a82db62402cff1d1a53430a2c9183ddbe6398","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_unicarbkb.csv","filename":"rat_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_unicarbkb.stat.csv","filename":"rat_protein_xref_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":415,"last_update":"2024-05-17T11:23:54.015593Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000259/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000259/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.986196","modified":"2022-09-26T09:04:47.941156","version":"v-2.0.2"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_unicarbkb.csv","filename":"rat_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref UniCarbKB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"etag":"4e2412824d54693bb3d0b74dccb5cd438ac9bbc73916016039299a4bd20e5047","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_unicarbkb.csv","filename":"rat_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_unicarbkb.stat.csv","filename":"rat_protein_xref_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.283000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000259/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000259/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.986196","modified":"2022-09-26T09:04:47.941156","version":"v-2.1.1"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_unicarbkb.csv","filename":"rat_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref UniCarbKB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"etag":"9761eb4cb1f6353ecc5889fb6101f912","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_unicarbkb.csv","filename":"rat_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_unicarbkb.stat.csv","filename":"rat_protein_xref_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:10.246000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000260/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000260/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.987144","modified":"2024-05-17T11:23:54.057Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Reactome dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"0678b88dd4248603fedd55f8c90914dc994f63973398a7dfc946f52ee3646c68","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_reactome.csv","filename":"rat_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_reactome.stat.csv","filename":"rat_protein_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2024-05-17T11:23:54.057842Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000260/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000260/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.987144","modified":"2022-09-26T09:04:47.987292","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_reactome.csv","filename":"rat_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Reactome contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"34f247827dcef99fbf2a3a08fcdcd50f6b0a1a575c7e8300d01bed3d213f33e4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_reactome.csv","filename":"rat_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_reactome.stat.csv","filename":"rat_protein_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.211000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000260/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000260/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Reactome","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.987144","modified":"2022-09-26T09:04:47.987292","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_reactome.csv","filename":"rat_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Reactome contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"0fe826aba77b148870405e8406f55067","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_reactome.csv","filename":"rat_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_reactome.stat.csv","filename":"rat_protein_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:10.429000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000261/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000261/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.988053","modified":"2024-05-17T11:23:54.098Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref PANTHER dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products. "],"etag":"3cf8283ba9defa68da217f2b20ca15f7134f0fe9b8a5f06fb56cff191ba13212","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_panther.csv","filename":"rat_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_panther.stat.csv","filename":"rat_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":479,"last_update":"2024-05-17T11:23:54.098336Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000261/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000261/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.988053","modified":"2022-09-26T09:04:47.981209","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_panther.csv","filename":"rat_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref PANTHER contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products. "],"etag":"38154c46a24ccd77413376d5e34c22d76dc10ceca5148abe13d2f742821324ff","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_panther.csv","filename":"rat_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_panther.stat.csv","filename":"rat_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.446000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000261/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000261/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PANTHER","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.988053","modified":"2022-09-26T09:04:47.981209","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_panther.csv","filename":"rat_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref PANTHER contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products. "],"etag":"78b2c32a9a75e6bedc7658c601f58581","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_panther.csv","filename":"rat_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_panther.stat.csv","filename":"rat_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:10.625000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000262/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000262/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.988943","modified":"2024-05-17T11:23:54.137Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref PRO contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"etag":"d9f2e77d18ebb6ed0aa802d7f64fd3d9e686427eb0628b0319d8e49a76879b8d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_pro.csv","filename":"rat_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_pro.stat.csv","filename":"rat_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":391,"last_update":"2024-05-17T11:23:54.137025Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000262/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000262/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.988943","modified":"2022-09-26T09:04:47.951266","version":"v-2.0.2"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_pro.csv","filename":"rat_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref PRO contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"etag":"c23918bda78d5d3150f8f67e02872daca27d8c6050071f846344045af5fcbf38","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_pro.csv","filename":"rat_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_pro.stat.csv","filename":"rat_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.232000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000262/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000262/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PRO","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.988943","modified":"2022-09-26T09:04:47.951266","version":"v-2.1.1"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_pro.csv","filename":"rat_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref PRO contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"etag":"d7300acc2489160d55a0d71a737cd6a2","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pro.csv","filename":"rat_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pro.stat.csv","filename":"rat_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:10.818000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000263/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000263/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.989848","modified":"2024-05-17T11:23:54.177Z","version":"v-0.0.0"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref IntAct dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"c9ddabdcc429d1d70fa20288bdbc1bc056ed4feecdeebc7bb7d670ddc98e8838","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_intact.csv","filename":"rat_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_intact.stat.csv","filename":"rat_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":533,"last_update":"2024-05-17T11:23:54.177698Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000263/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000263/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.989848","modified":"2022-09-26T09:04:47.935241","version":"v-2.0.2"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_intact.csv","filename":"rat_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref IntAct dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"0630aebf8ecae642c2b196101b294b2954cde339aa06fc46cb2196d76d65a8fa","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_intact.csv","filename":"rat_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_intact.stat.csv","filename":"rat_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.888000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000263/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000263/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.989848","modified":"2022-09-26T09:04:47.935241","version":"v-2.1.1"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_intact.csv","filename":"rat_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref IntAct dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"etag":"a2cea73d09d804629e310b1aa4c26b13","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_intact.csv","filename":"rat_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_intact.stat.csv","filename":"rat_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:11.010000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000264/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000264/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.990766","modified":"2024-05-17T11:23:54.217Z","version":"v-0.0.0"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Citations (RefSeq) datasets contains Rattus norvegicus [taxid:10116] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"f95374c5899158c2e4a1b325dd9252e71db28f7bdf822d93b689a639aa96cbde","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_citations_refseq.stat.csv","filename":"rat_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":315,"last_update":"2024-05-17T11:23:54.217667Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000264/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000264/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.990766","modified":"2022-09-26T09:04:47.917146","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Citations (RefSeq) datasets contains rat [taxid:10116] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"92ad3fea92b680b5de1f5535ba4d13e2d5092a18146851158577c8597b5bbf2d","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_function_refseq.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_refseq.stat.csv","filename":"rat_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.484000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000264/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000264/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.990766","modified":"2022-09-26T09:04:47.917146","version":"v-2.1.1"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Citations (RefSeq) datasets contains rat [taxid:10116] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"b5c095d81682c85bc0104ed2c2a2406e","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_function_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_refseq.stat.csv","filename":"rat_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:11.186000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000265/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000265/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.991804","modified":"2024-06-03T20:50:58.673Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Rattus norvegicus [taxid:10116] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"24c748dec5e11bddec016947ed6a5b0bb53b7ad6f11726fc0173517595536679","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_altnames.csv","filename":"rat_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_altnames.stat.csv","filename":"rat_protein_altnames.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":227,"last_update":"2024-06-03T20:50:58.673814Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000265/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000265/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.991804","modified":"2022-09-26T09:04:47.887852","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_altnames.csv","filename":"rat_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for rat [taxid:10116] proteins. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d137daa5df74a6583d2c02174ab6a55cb719618d47566824758835fe4659d348","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_altnames.csv","filename":"rat_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_altnames.stat.csv","filename":"rat_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.520000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000265/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000265/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.991804","modified":"2022-09-26T09:04:47.887852","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_altnames.csv","filename":"rat_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for rat [taxid:10116] proteins. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1363c888303f526f8c5b9b2039067b19","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_altnames.csv","filename":"rat_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_altnames.stat.csv","filename":"rat_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:11.370000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000266/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000266/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.992721","modified":"2024-05-17T11:23:54.297Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Bgee dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"etag":"0d65d8652e70204835ec0cc662d1410fa091219c7a76f245d39ffa51c11c394d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_bgee.csv","filename":"rat_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_bgee.stat.csv","filename":"rat_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":475,"last_update":"2024-05-17T11:23:54.297201Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000266/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000266/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.992721","modified":"2022-09-26T09:04:48.023514","version":"v-2.0.2"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_bgee.csv","filename":"rat_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Bgee dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"etag":"794a49f8565a0e5241b6eb2032fcc98ef45674366320ed52e333b7eab517b1db","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_bgee.csv","filename":"rat_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_bgee.stat.csv","filename":"rat_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.823000Z","access_count":37},{"object_id":"https://biocomputeobject.org/GLY_000266/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000266/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Bgee","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.992721","modified":"2022-09-26T09:04:48.023514","version":"v-2.1.1"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_bgee.csv","filename":"rat_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniProtKB Xref Bgee dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"etag":"804d2bf33cd53eeb0d1ace7f4cce770c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_bgee.csv","filename":"rat_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_bgee.stat.csv","filename":"rat_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:11.555000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000267/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000267/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.993695","modified":"2024-05-17T11:23:54.340Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene coordinates","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Gene Locus (Ensembl) contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions mapped to the corresponding ENSEMBL Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"947c3c67ffcaf190c04d09018052d60a5854d770d98fd4c09747aff6c9c3b6b7","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_genelocus.csv","filename":"rat_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_genelocus.stat.csv","filename":"rat_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":388,"last_update":"2024-05-17T11:23:54.340083Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000267/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000267/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.993695","modified":"2022-09-26T09:04:48.000439","version":"v-2.0.2"},"description_domain":{"keywords":["gene coordinates","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/v-1.12.3/sourceuniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_genelocus.csv","filename":"rat_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Gene Locus (Ensembl) contains rat [taxid:10116] UniProtKB canonical accessions mapped to the corresponding ENSEMBL Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"92c1d323ac23949674ca43eafdf9e52ac1ba3ada2367faed6f507de5b07909d6","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"Rattus_norvegicus.Rnor_6.0.95.gtf","uri":"https:/data.glygen.org/ln2downloads/ucsc/gtf/Rattus_norvegicus.Rnor_6.0.95.gtf"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_genelocus.csv","filename":"rat_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_genelocus.stat.csv","filename":"rat_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.642000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000267/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000267/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Locus (Ensembl)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.993695","modified":"2022-09-26T09:04:48.000439","version":"v-2.1.1"},"description_domain":{"keywords":["gene coordinates","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/v-1.12.3/sourceuniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_genelocus.csv","filename":"rat_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Gene Locus (Ensembl) contains rat [taxid:10116] UniProtKB canonical accessions mapped to the corresponding ENSEMBL Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"eb8b482257ee8c6a72fff7f4badfe92b","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"Rattus_norvegicus.Rnor_6.0.95.gtf","uri":"/data/shared/glyds/downloads/ucsc/gtf/Rattus_norvegicus.Rnor_6.0.95.gtf"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_genelocus.csv","filename":"rat_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_genelocus.stat.csv","filename":"rat_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:11.745000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000268/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000268/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2e1d1479c3c447e3a4f90c80a98233779a352a4df64ce9bf8282a12c214ff404","provenance_domain":{"name":"Human Tyr O-Linked Glycosylation Sites","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.994596","modified":"2024-12-10T17:01:04.176Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Tyr O-Linked Glycosylation Sites dataset contains Homo sapiens [taxid:9606] UniProtKB accessions that are Tyr O-Linked Glycosylated. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. If you use this dataset please provide proper attribution to GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position of glycosylation against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries."}],"keywords":["tyrosine","o-linked glycosylation","glycosylation sites"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":449,"last_update":"2024-12-10T17:01:04.176408Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000268/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000268/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Tyr O-Linked Glycosylation Sites","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.994596","modified":"2022-09-26T09:04:47.907359","version":"v-2.0.2"},"description_domain":{"keywords":["tyrosine","o-linked glycosylation","glycosylation sites"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position of glycosylation against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Human Tyr O-Linked Glycosylation Sites dataset contains human [taxid:9606] UniProtKB accessions that are Tyr O-Linked Glycosylated. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. If you use this dataset please provide proper attribution to GlyGen"],"etag":"c755bd881ebc3cf1c6ebd452698e6d4cd88a32ea2291962c020744e8f6fd90c5","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.355000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000268/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000268/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Tyr O-Linked Glycosylation Sites","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.994596","modified":"2022-09-26T09:04:47.907359","version":"v-2.1.1"},"description_domain":{"keywords":["tyrosine","o-linked glycosylation","glycosylation sites"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position of glycosylation against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Human Tyr O-Linked Glycosylation Sites dataset contains human [taxid:9606] UniProtKB accessions that are Tyr O-Linked Glycosylated. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. If you use this dataset please provide proper attribution to GlyGen"],"etag":"08f670e41fdf2f0c2d937d9ca60cee54","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:11.946000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000269/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000269/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.995531","modified":"2024-06-03T20:36:30.610Z","version":"v-0.0.0"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Mus musculus [taxid:10090] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen. "],"etag":"0ac6d8ce7c9504b7e0a3b3f6be5c4cf90e351118668e1d01e7c108699daee343","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycosylation_motifs.csv","filename":"mouse_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycosylation_motifs.stat.csv","filename":"mouse_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":408,"last_update":"2024-06-03T20:36:30.610529Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000269/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000269/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.995531","modified":"2022-09-26T09:04:47.892437","version":"v-2.0.2"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_glycosylation_motifs.csv","filename":"mouse_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for mouse [taxid:10090] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen. The dataset is derived form 2019-09 UniprotKB release."],"etag":"c42f1ff4c190ef5e5a5cad1bee7a4b55d8090db5a715964cf8df2a1c76e6d7cc","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycosylation_motifs.csv","filename":"mouse_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycosylation_motifs.stat.csv","filename":"mouse_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.783000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000269/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000269/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.995531","modified":"2022-09-26T09:04:47.892437","version":"v-2.1.1"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_glycosylation_motifs.csv","filename":"mouse_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for mouse [taxid:10090] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen. The dataset is derived form 2019-09 UniprotKB release."],"etag":"7e66420522f7031a41a9b0e50c442531","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycosylation_motifs.csv","filename":"mouse_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycosylation_motifs.stat.csv","filename":"mouse_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:12.133000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000270/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000270/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.996476","modified":"2024-05-17T11:23:54.457Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref BRENDA contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"5182d0088b3cee86bfdff8029e993d33b49301be72436027ffd4030bbbde4046","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_brenda.csv","filename":"rat_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_brenda.stat.csv","filename":"rat_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":480,"last_update":"2024-05-17T11:23:54.457833Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000270/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000270/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.996476","modified":"2022-09-26T09:04:48.031912","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_brenda.csv","filename":"rat_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref BRENDA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"6d52d03e620d5c0c0814a2357117765eb547524eef52b657bc16ae6c49d8942f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_brenda.csv","filename":"rat_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_brenda.stat.csv","filename":"rat_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.979000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000270/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000270/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.996476","modified":"2022-09-26T09:04:48.031912","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_brenda.csv","filename":"rat_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat UniprotKB Xref BRENDA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"a80aa7770f938fb6a4f4af022357450e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_brenda.csv","filename":"rat_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_brenda.stat.csv","filename":"rat_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:12.320000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000272/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000272/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.998256","modified":"2024-06-03T20:36:54.538Z","version":"v-0.0.0"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Rattus norvegicus [taxid:10116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen."],"etag":"155de441bfa5ccfca91c81c863df2e1bd75e13885e74623d9c80ec23096bee78","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_glycosylation_motifs.csv","filename":"rat_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_glycosylation_motifs.stat.csv","filename":"rat_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":410,"last_update":"2024-06-03T20:36:54.538690Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000272/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000272/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.998256","modified":"2022-09-26T09:04:47.915182","version":"v-2.0.2"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_glycosylation_motifs.csv","filename":"rat_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for rat [taxid:10116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen. The dataset is derived form 2019-09 UniprotKB release."],"etag":"3deb3febd63624f3b4b48410155bcf5c3d12a655856d2ecb8411d2b3376e0f2b","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_glycosylation_motifs.csv","filename":"rat_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_glycosylation_motifs.stat.csv","filename":"rat_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.822000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000272/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000272/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.998256","modified":"2022-09-26T09:04:47.915182","version":"v-2.1.1"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_glycosylation_motifs.csv","filename":"rat_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for rat [taxid:10116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen. The dataset is derived form 2019-09 UniprotKB release."],"etag":"a57f37ffa977e77e3a02affad5bb6ad5","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_glycosylation_motifs.csv","filename":"rat_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_glycosylation_motifs.stat.csv","filename":"rat_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:12.508000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000273/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000273/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rgd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RGD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:38.999441","modified":"2024-05-17T11:23:54.537Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rat Genome Database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The rat UniprotKB Xref RefSeq dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to Rat Genome Database (RGD) accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Rat Genome Database (RGD) is the premier site for genetic, genomic, phenotype, and disease data generated from rat research"],"etag":"b6d979224209bcdaac31499a8f95c2fecf85bbbbc408391f6ebc422b78589637","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_rgd.csv","filename":"rat_protein_xref_rgd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_rgd.stat.csv","filename":"rat_protein_xref_rgd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":398,"last_update":"2024-05-17T11:23:54.537172Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000273/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000273/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rgd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RGD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:38.999441","modified":"2022-09-26T09:04:47.888755","version":"v-2.0.2"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_rgd.csv","filename":"rat_protein_xref_rgd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rat Genome Database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced to Rat Genome Database (RGD) accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. f you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Rat Genome Database (RGD) is the premier site for genetic, genomic, phenotype, and disease data generated from rat research"],"etag":"04e09b40e34ed9a19cebcdebec724706f18cff522131e0b15e7fb7c912fdfbfb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_rgd.csv","filename":"rat_protein_xref_rgd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_rgd.stat.csv","filename":"rat_protein_xref_rgd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.291000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000273/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000273/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rgd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RGD","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:38.999441","modified":"2022-09-26T09:04:47.888755","version":"v-2.1.1"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_rgd.csv","filename":"rat_protein_xref_rgd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rat Genome Database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced to Rat Genome Database (RGD) accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. f you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Rat Genome Database (RGD) is the premier site for genetic, genomic, phenotype, and disease data generated from rat research"],"etag":"11fd9ba4016c8d308236abe19176dd11","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_rgd.csv","filename":"rat_protein_xref_rgd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_rgd.stat.csv","filename":"rat_protein_xref_rgd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:12.701000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000274/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000274/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:39.000407","modified":"2024-05-17T11:23:54.582Z","version":"v-0.0.0"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Human Phosphorylation Sites (UniProtKB) dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"c1b55d35f1a15c252c38ccfb74524c69f9e015180ce72936d8c1514908b313a7","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":309,"last_update":"2024-05-17T11:23:54.582627Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000274/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000274/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:39.000407","modified":"2022-09-26T09:04:47.948889","version":"v-2.0.2"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Human Phosphorylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"abc8ca878bb0840a84c574704de1911e7a6cdea199a32226595cea378f25c48a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.317000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000274/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000274/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:39.000407","modified":"2022-09-26T09:04:47.948889","version":"v-2.1.1"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Human Phosphorylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8b54f8d2f1be5dea5c6ba824804fd204","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:12.887000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000275/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000275/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:39.001496","modified":"2024-05-17T11:23:54.625Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Information (NCBI RefSeq) dataset contains Rattus norvegicus [taxid:10116] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"15fb5c24a1e4cf2b30fd1f387e4ff6905ba6ab395ea8ae7d0b4ea2d154eacda3","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_info_refseq.stat.csv","filename":"rat_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":291,"last_update":"2024-05-17T11:23:54.625124Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000275/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000275/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:39.001496","modified":"2022-09-26T09:04:47.937314","version":"v-2.0.2"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Information (NCBI RefSeq) dataset contains rat [taxid:10116] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"e40d8b4fa722f1501f9442aacf56ddde9fe8b11662ae979b58dcaee3459fb1d8","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10116.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_10116.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_info_refseq.stat.csv","filename":"rat_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.071000Z","access_count":58},{"object_id":"https://biocomputeobject.org/GLY_000275/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000275/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:39.001496","modified":"2022-09-26T09:04:47.937314","version":"v-2.1.1"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Information (NCBI RefSeq) dataset contains rat [taxid:10116] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"cfd0b703c2999ad9db7c557e2e5a1d00","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_10116.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_10116.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_info_refseq.stat.csv","filename":"rat_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:13.073000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000276/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000276/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T14:06:39.002473","modified":"2024-05-17T11:23:54.666Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat  UniprotKB Xref RefSeq dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"etag":"8d76cec830fffe41e407a1972b53b76fe9e91aacaab283a97fa64160f762a2b5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_refseq.stat.csv","filename":"rat_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":571,"last_update":"2024-05-17T11:23:54.666501Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000276/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000276/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T14:06:39.002473","modified":"2022-09-26T09:04:47.989112","version":"v-2.0.2"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"etag":"8037e8b9681b531e0a215eab0fcfe304166836a04937c0445da267fa81208be8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.stat.csv","filename":"rat_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.956000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000276/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000276/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T14:06:39.002473","modified":"2022-09-26T09:04:47.989112","version":"v-2.1.1"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"etag":"a2fc3cafbebe58242905d714ce124159","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.stat.csv","filename":"rat_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:13.263000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000278/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000278/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-09-06T17:38:32.808468","modified":"2024-05-17T11:23:54.704Z","version":"v-0.0.0"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat EBI-UniProtKB NT dataset contains proteome data for Rattus norvegicus [taxid:10116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"a0edd94c2b25e89f48c2269ca5f160e3178032411f42135c58496579b3027f3b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_ntdata.nt","filename":"rat_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_ntdata.stat.csv","filename":"rat_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":278,"last_update":"2024-05-17T11:23:54.704626Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000278/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000278/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-06T17:38:32.808468","modified":"2022-09-26T09:04:47.962506","version":"v-2.0.2"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/urat_protein_ntdata.nt","filename":"rat_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat EBI-UniProtKB NT file contains proteome data for rat [taxid:10116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7feaf2629062d9a4b6e0a45700c9580c2706aed850cdd50188408234a73dfa34","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_ntdata.nt","filename":"rat_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_ntdata.stat.csv","filename":"rat_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.578000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000278/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000278/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-06T17:38:32.808468","modified":"2022-09-26T09:04:47.962506","version":"v-2.1.1"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/urat_protein_ntdata.nt","filename":"rat_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat EBI-UniProtKB NT file contains proteome data for rat [taxid:10116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7b55adb8894e51551e39936a640b57c0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_ntdata.nt","filename":"rat_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_ntdata.stat.csv","filename":"rat_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:13.455000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000279/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000279/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a35877c832911df5bf67ad1aa47265f44e4f145509cd37c918528f603884613e","provenance_domain":{"name":"Rat Glycosyltransferases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-11T17:14:40.100826","modified":"2024-12-10T18:50:49.282Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycosyltransferases dataset contains list of Rattus norvegicus [taxid:10116] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. If you use this dataset please provide proper attribution to GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_glycosyltransferase.stat.csv","filename":"rat_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":596,"last_update":"2024-12-10T18:50:49.282641Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000279/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000279/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosyltransferases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-11T17:14:40.100826","modified":"2022-09-26T09:04:47.926644","version":"v-2.0.2"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Glycosyltransferases dataset contains list of rat [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. If you use this dataset please provide proper attribution to GlyGen"],"etag":"2378738c007b36bee90cb9dca17659bb8529ac7514a5c2e64efd2c7522e8e56a","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/rat_protein_glycosyltransferase.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_glycosyltransferase.stat.csv","filename":"rat_protein_glycosyltransferase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.205000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000279/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000279/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosyltransferases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-11T17:14:40.100826","modified":"2022-09-26T09:04:47.926644","version":"v-2.1.1"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Glycosyltransferases dataset contains list of rat [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. If you use this dataset please provide proper attribution to GlyGen"],"etag":"77926d415d30f1f78f4c5a1646812784","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/rat_protein_glycosyltransferase.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_glycosyltransferase.stat.csv","filename":"rat_protein_glycosyltransferase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:13.641000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000280/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000280/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7cb0a12a95b5c5043217c110f890f44feed491d23cc2ef61c5dc99d127225a69","provenance_domain":{"name":"Rat Glycohydrolases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-11T17:20:18.184619","modified":"2024-12-10T18:55:18.682Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycohydrolases dataset contains a list of Rattus norvegicus [taxid:10116] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession"}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_glycohydrolase.stat.csv","filename":"rat_protein_glycohydrolase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":365,"last_update":"2024-12-10T18:55:18.682773Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000280/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000280/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycohydrolases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-09-11T17:20:18.184619","modified":"2022-09-26T09:04:47.922806","version":"v-2.0.2"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Glycohydrolases dataset contains a list of rat [taxid:9606] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7a1619201418108951365fbcccca2b381a223d76bd4f7d8471accfc64990d8a9","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/rat_protein_glycohydrolase.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_glycohydrolase.stat.csv","filename":"rat_protein_glycohydrolase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.306000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000280/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000280/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycohydrolases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-09-11T17:20:18.184619","modified":"2022-09-26T09:04:47.922806","version":"v-2.1.1"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Glycohydrolases dataset contains a list of rat [taxid:9606] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"33eb15084f7765a027ab2bd008975174","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/rat_protein_glycohydrolase.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_glycohydrolase.stat.csv","filename":"rat_protein_glycohydrolase.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:13.833000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000281/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000281/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"GlyGen-Glycan masterlist","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T12:43:51.676216","modified":"2024-05-17T11:23:54.821Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to process the dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on the glycan properties such as mass, permethylated mass, topology, base composition, composition and the number of monosaccharides for the associated glycan (GlyTouCan Accession). This dataset is the master-list of the GlyTouCan accessions currently present in GlyGen. Source database: https://glytoucan.org/"],"etag":"43ff28e8feeba335b1b941f5f6c179857dd94945756ff1f95bddaeba3c5a9472","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_masterlist.stat.csv","filename":"glycan_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":343,"last_update":"2024-05-17T11:23:54.821779Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000281/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000281/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"GlyGen-Glycan masterlist","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T12:43:51.676216","modified":"2022-09-26T09:04:47.964527","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to process the dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on the glycan properties such as mass, permethylated mass, topology, base composition, composition and the number of monosaccharides for the associated glycan (GlyTouCan Accession). This dataset is the master-list of the GlyTouCan accessions currently present in GlyGen. Source database: https://glytoucan.org/"],"etag":"50669a415f7cba2e4df70e08824c9e794272a7942a2337d1f8af8e63f3b4f8d8","io_domain":{"input_subdomain":[{"uri":{"filename":"allglycan.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/allglycan.tsv"}},{"uri":{"filename":"allmotifs.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/allmotifs.tsv"}},{"uri":{"filename":"glycan_properties.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/glycan_properties.tsv"}},{"uri":{"filename":"subsumption.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.stat.csv","filename":"glycan_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.017000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000281/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000281/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"GlyGen-Glycan masterlist","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T12:43:51.676216","modified":"2022-09-26T09:04:47.964527","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to process the dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on the glycan properties such as mass, permethylated mass, topology, base composition, composition and the number of monosaccharides for the associated glycan (GlyTouCan Accession). This dataset is the master-list of the GlyTouCan accessions currently present in GlyGen. Source database: https://glytoucan.org/"],"etag":"d178f4371a6963624e88de79431194b8","io_domain":{"input_subdomain":[{"uri":{"filename":"allglycan.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/allglycan.tsv"}},{"uri":{"filename":"allmotifs.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/allmotifs.tsv"}},{"uri":{"filename":"glycan_properties.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/glycan_properties.tsv"}},{"uri":{"filename":"pubs.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/pubs.tsv"}},{"uri":{"filename":"subsumption.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.stat.csv","filename":"glycan_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:14.038000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000282/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000282/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Classification","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Classification","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T12:59:46.920689","modified":"2024-05-17T11:23:54.861Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Classification"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on the glycan classification such as glycan type and sub-type for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"b68d480928c33981690839706d773e43890c8783f098a6aae26bf2f19191e89f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_classification.csv","filename":"glycan_classification.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_classification.stat.csv","filename":"glycan_classification.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":307,"last_update":"2024-05-17T11:23:54.861817Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000282/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000282/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Classification","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Classification","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T12:59:46.920689","modified":"2022-09-26T09:04:47.976046","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Classification"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/classification.tsv","filename":"classification.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_classification.csv","filename":"glycan_classification.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on the glycan classification such as glycan type and sub-type for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"6acda041653cffb786ee565e62c909e2aea578574450c21e08563a1bac361346","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"classification.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/classification.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_classification.csv","filename":"glycan_classification.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_classification.stat.csv","filename":"glycan_classification.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.421000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000282/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000282/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Classification","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Classification","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T12:59:46.920689","modified":"2022-09-26T09:04:47.976046","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Classification"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/classification.tsv","filename":"classification.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_classification.csv","filename":"glycan_classification.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on the glycan classification such as glycan type and sub-type for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"7c81925af44a4d6e75348feb32232709","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"classification.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/classification.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_classification.csv","filename":"glycan_classification.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_classification.stat.csv","filename":"glycan_classification.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:14.232000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000283/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000283/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"43e1ca351828e4397fb357de1a6c456326351c30c55ac492485f36eb743520ae","provenance_domain":{"name":"Glycan Motif","version":"v-0.0.0","created":"2019-11-13T13:05:37.256972","modified":"2024-05-17T11:23:54.903Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides information on the glycan motifs for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281) and from GlycoMotif (https://glycomotif.glyomics.org/)."],"description_domain":{"keywords":["Glycan","Motif","Glycomotif"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list.The data incudes curated list of the motif accessions and other information like: motif name,reducing end,alternative name,aglycon."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_motif.csv","filename":"glycan_motif.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_motif.stat.csv","filename":"glycan_motif.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Motif","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":280,"last_update":"2024-05-17T11:23:54.903313Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000283/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000283/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Motif","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Motif","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T13:05:37.256972","modified":"2022-09-26T09:04:47.993129","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","Motif"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/allmotifs.tsv","filename":"allmotifs.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/allmotifaligns.tsv","filename":"allmotifaligns.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_motif.csv","filename":"glycan_motif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list.The data incudes curated list of the motif accessions and other information like: motif name,reducing end,alternative name,aglycon."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on the glycan motifs for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"f3923c64331bad42bab91bbdbbad7a9d9e6fd9e4d39deb5b20eec7d24c99e1d2","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"allmotifaligns.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/allmotifaligns.tsv"}},{"uri":{"filename":"allmotifs.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/allmotifs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_motif.csv","filename":"glycan_motif.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_motif.stat.csv","filename":"glycan_motif.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.143000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000283/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000283/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8dd54862fb6f50fa78d44421f26d2ef2","provenance_domain":{"name":"Glycan Motif","version":"v-2.1.1","created":"2019-11-13T13:05:37.256972","modified":"2023-03-07T02:28:55.265Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides information on the glycan motifs for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281) and from GlycoMotif (https://glycomotif.glyomics.org/)."],"description_domain":{"keywords":["Glycan","Motif","Glycomotif"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/allmotifs.tsv","filename":"allmotifs.tsv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/allmotifaligns.tsv","filename":"allmotifaligns.tsv"}],"output_list":[{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_motif.csv","filename":"glycan_motif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list.The data incudes curated list of the motif accessions and other information like: motif name,reducing end,alternative name,aglycon."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"allmotifaligns.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/allmotifaligns.tsv"}},{"uri":{"filename":"allmotifs.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/allmotifs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_motif.csv","filename":"glycan_motif.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_motif.stat.csv","filename":"glycan_motif.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Motif","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:14.430000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000284/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000284/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Biosynthetic Enzyme","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Enzyme","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Allison Nairn","email":"avnairn@uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T13:19:08.883378","modified":"2024-05-17T11:23:54.942Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Enzyme"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the source authors and a python script was used to extract columns: glytoucan_ac,residue_name,residue_id,uniprot,gene_name,gene_id,parent_residue_id,type,species. The script also assigned protein recommended name based on the UniProtKB accession. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are human or mouse proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the Glyco tree model. The glycans listed in the database may or may not have a human (TaxID:9606) or mouse (TaxID:10090) species annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a human or mouse biosynthetic enzyme association should not be considered as a human or mouse species annotation for that glycan."],"etag":"3a19ee0207fa13935b9fa2aaba8da59599362781073dcf112a922564c3a36c83","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_enzyme.stat.csv","filename":"glycan_enzyme.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":657,"last_update":"2024-05-17T11:23:54.942689Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000284/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000284/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Biosynthetic Enzyme","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Enzyme","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Allison Nairn","email":"avnairn@uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T13:19:08.883378","modified":"2022-09-26T09:04:48.014559","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Enzyme"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/annotated_glycans.csv","filename":"annotated_glycans.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_protein_recnames.csv","filename":"human_protein_recnames.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}],"prerequisite":[],"description":"The input file was downloaded from the source authors and a python script was used to extract columns: glytoucan_ac,residue_name,residue_id,uniprot,gene_name,gene_id,parent_residue_id,type,species. The script also assigned protein recommended name based on the UniProtKB accession. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are human or mouse proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the Glyco tree model. The glycans listed in the database may or may not have a human (TaxID:9606) or mouse (TaxID:10090) species annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a human or mouse biosynthetic enzyme association should not be considered as a human or mouse species annotation for that glycan."],"etag":"a63c80769eb24e433e2b1549473ce4b085ed61f2443f00de26f325ef389bd06b","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_recnames.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_recnames.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_recnames.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_recnames.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_recnames.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_recnames.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_recnames.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_recnames.csv"}},{"uri":{"filename":"glycotree_annotated_glycans.tsv","uri":"https:/data.glygen.org/ln2downloads/sandbox/02_06_2022/glycotree_annotated_glycans.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_enzyme.stat.csv","filename":"glycan_enzyme.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.330000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000284/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000284/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Biosynthetic Enzyme","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Rattus"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Enzyme","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Allison Nairn","email":"avnairn@uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T13:19:08.883378","modified":"2022-09-26T09:04:48.014559","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Enzyme"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/annotated_glycans.csv","filename":"annotated_glycans.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_protein_recnames.csv","filename":"human_protein_recnames.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}],"prerequisite":[],"description":"The input file was downloaded from the source authors and a python script was used to extract columns: glytoucan_ac,residue_name,residue_id,uniprot,gene_name,gene_id,parent_residue_id,type,species. The script also assigned protein recommended name based on the UniProtKB accession. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are human or mouse proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the Glyco tree model. The glycans listed in the database may or may not have a human (TaxID:9606) or mouse (TaxID:10090) species annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a human or mouse biosynthetic enzyme association should not be considered as a human or mouse species annotation for that glycan."],"etag":"4b2d33efe6481f3691ba223b8a0ade74","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_recnames.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_recnames.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_recnames.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_recnames.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_recnames.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_recnames.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_recnames.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_recnames.csv"}},{"uri":{"filename":"glycotree_annotated_glycans.tsv","uri":"/data/shared/glyds/downloads/sandbox/05_17_2023/glycotree_annotated_glycans.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_enzyme.stat.csv","filename":"glycan_enzyme.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:14.630000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000285/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000285/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Citations (GlyTouCan)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T13:26:29.074237","modified":"2024-05-17T11:23:54.981Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlyTouCan and UniCarbKB database.The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.unicarbkb.org/"],"etag":"95cebbe37fdb237661857eefcbbe21f734e758ebf1f85dbbbfb488bd169a13b6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_glytoucan.stat.csv","filename":"glycan_citations_glytoucan.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":308,"last_update":"2024-05-17T11:23:54.981867Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000285/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000285/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Citations (GlyTouCan)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T13:26:29.074237","modified":"2022-09-26T09:04:48.017345","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/pubs.tsv","filename":"pubs.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlyTouCan and UniCarbKB database.The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.unicarbkb.org/"],"etag":"44ce71539b6580836fa5f10a38527956a72f3e57272d00d9417c7b0f317e53c6","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"pubs.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/pubs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_glytoucan.stat.csv","filename":"glycan_citations_glytoucan.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.981000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000285/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000285/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Citations (GlyTouCan)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T13:26:29.074237","modified":"2022-09-26T09:04:48.017345","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/pubs.tsv","filename":"pubs.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlyTouCan and UniCarbKB database.The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.unicarbkb.org/"],"etag":"bb2d11ed574f81d716c9a68caea6980d","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"pubs.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/pubs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_glytoucan.stat.csv","filename":"glycan_citations_glytoucan.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:14.821000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000286/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000286/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Monosaccharide compositions","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T13:36:02.199874","modified":"2024-05-17T11:23:55.017Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Monosaccharide Composition"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"8e3ce352852ce29ee8b216a4dd718aaa9e1848517a19b5a7ba58611352d19d3f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_monosaccharide_composition.stat.csv","filename":"glycan_monosaccharide_composition.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":460,"last_update":"2024-05-17T11:23:55.017292Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000286/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000286/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Monosaccharide compositions","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T13:36:02.199874","modified":"2022-09-26T09:04:47.891582","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Monosaccharide Composition"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/monocomp.tsv","filename":"monocomp.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"2c25e9312352c1ce1215318c6413b1941fa651e771b15c3f60ea60feba227282","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_monosaccharide_composition.stat.csv","filename":"glycan_monosaccharide_composition.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.547000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000286/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000286/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Monosaccharide compositions","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T13:36:02.199874","modified":"2022-09-26T09:04:47.891582","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Monosaccharide Composition"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/monocomp.tsv","filename":"monocomp.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"47b59e2358011a112afd543150a7829c","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_monosaccharide_composition.stat.csv","filename":"glycan_monosaccharide_composition.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:15.022000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000287/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000287/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0c1542df584520655dd2aab047a2f6ab536716ed0d4faa3fb6f925a97a53325e","provenance_domain":{"name":"Glycan Sequences Glycam IUPAC","version":"v-0.0.0","created":"2019-11-13T16:15:24.688189","modified":"2024-05-17T11:23:55.057Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in Glycam IUPAC format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://dev.glycam.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycam IUPAC"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_glycam_iupac.csv","filename":"glycan_sequences_glycam_iupac.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_glycam_iupac.stat.csv","filename":"glycan_sequences_glycam_iupac.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM IUPAC sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":278,"last_update":"2024-05-17T11:23:55.057892Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000287/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000287/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM IUPAC sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences Glycam IUPAC","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:15:24.688189","modified":"2022-09-26T09:04:47.905596","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycam IUPAC"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_sequences_glycam_iupac.csv","filename":"glycan_sequences_glycam_iupac.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in Glycam IUPAC format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://dev.glycam.org/"],"etag":"8d1ec97b38b35301deab868df81392458e3572ed8256d3a37c95facbe2f0f868","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_glycam_iupac.csv","filename":"glycan_sequences_glycam_iupac.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_glycam_iupac.stat.csv","filename":"glycan_sequences_glycam_iupac.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.962000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000287/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000287/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bbbe5e4443b22fd5f9482cad5254b214","provenance_domain":{"name":"Glycan Sequences Glycam IUPAC","version":"v-2.1.1","created":"2019-11-13T16:15:24.688189","modified":"2022-10-12T16:29:46.804Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in Glycam IUPAC format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://dev.glycam.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycam IUPAC"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/monocomp.tsv","filename":"monocomp.tsv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/glycam_iupac.zip","filename":"glycam_iupac.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_sequences_glycam_iupac.csv","filename":"glycan_sequences_glycam_iupac.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_glycam_iupac.csv","filename":"glycan_sequences_glycam_iupac.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_glycam_iupac.stat.csv","filename":"glycan_sequences_glycam_iupac.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM IUPAC sequence format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:07:32.350000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000288/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000288/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f68b0229541c82ca60caf5161be92263766621f46f821dacb242024dd8a049e1","provenance_domain":{"name":"Glycan Sequences GlycoCT","version":"v-0.0.0","created":"2019-11-13T16:21:17.865259","modified":"2024-05-17T11:23:55.097Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in GlycoCT format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoCT"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_glycoct.csv","filename":"glycan_sequences_glycoct.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_glycoct.stat.csv","filename":"glycan_sequences_glycoct.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCT sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":272,"last_update":"2024-05-17T11:23:55.097738Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000288/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000288/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCT sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences GlycoCT","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:21:17.865259","modified":"2022-09-26T09:04:48.002286","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoCT"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycoct.zip","filename":"glycoct.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_sequences_glycoct.csv","filename":"glycan_sequences_glycoct.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in GlycoCT format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"3aadcb7d49dbb11e5b767c0bb2d19ac9110c1d8d1c214c05f87c0f5e769be490","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_glycoct.csv","filename":"glycan_sequences_glycoct.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_glycoct.stat.csv","filename":"glycan_sequences_glycoct.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.509000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000288/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000288/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"779460d04e1d0888b32f033e94f38c95","provenance_domain":{"name":"Glycan Sequences GlycoCT","version":"v-2.1.1","created":"2019-11-13T16:21:17.865259","modified":"2022-10-12T16:31:53.344Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in GlycoCT format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoCT"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/monocomp.tsv","filename":"monocomp.tsv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/glycoct.zip","filename":"glycoct.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_sequences_glycoct.csv","filename":"glycan_sequences_glycoct.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_glycoct.csv","filename":"glycan_sequences_glycoct.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_glycoct.stat.csv","filename":"glycan_sequences_glycoct.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCT sequence format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:07:32.545000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000289/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000289/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"826eacc069c12bdf4a5c2c8f7cf02ce56c0dc9ed349620500c7b492f1cdab536","provenance_domain":{"name":"Glycan Sequences InChI","version":"v-0.0.0","created":"2019-11-13T16:26:03.109539","modified":"2024-05-17T11:23:55.142Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the sequences in InChI format and InChI key for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping dataset (https://data.glygen.org/GLY_000305). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). InChI sequences and keys are retrieved from the PubChem ftp site (ftp://ftp.ncbi.nlm.nih.gov/pubchem/Compound/CURRENT-Full/SDF/)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","InChI","PubChem"],"platform":[],"pipeline_steps":[{"name":"dataset-maker/pubchem-download-step1.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[{"name":"","uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/pubchem-download-step1.py","filename":"","access_time":"","sha1_checksum":""}}],"description":"The GlyTouCan to PubChem CID mapping file was used download sdf PubChem compound files from the PubChem CID ftp site. Python scripts were used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."},{"step_number":"2","name":"pubchem-download-step2.py","description":"","prerequisite":[{"name":"","uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/pubchem-download-step2.py"}}],"input_list":[],"output_list":[]},{"step_number":"3","name":"pubchem-download-step3.py","description":"","prerequisite":[{"name":"","uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/pubchem-download-step3.py"}}],"input_list":[],"output_list":[]},{"step_number":"4","name":"pubchem-download-step4.py","description":"","prerequisite":[{"name":"","uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/pubchem-download-step4.py"}}],"input_list":[],"output_list":[]},{"step_number":"5","name":"make-species-agnostic-dataset.py","description":"","prerequisite":[{"name":"","uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py"}}],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_inchi.stat.csv","filename":"glycan_sequences_inchi.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"InChI Sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":458,"last_update":"2024-05-17T11:23:55.142038Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000289/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000289/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"InChI Sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences InChI","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:26:03.109539","modified":"2022-09-26T09:04:48.030465","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","InChI"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}],"prerequisite":[],"description":"The GlyTouCan Ac. to PubChem CID mapping file was used download .sdf PubChem compound files from PubChem CID ftp and a python script was used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the InChI key and glycan sequences in InChI format  for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000281). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"etag":"7922ffd82a9af44b99d95f6a7babd8601be23a7eb80d67205bfa13ba1e8ec8d0","io_domain":{"input_subdomain":[{"uri":{"filename":"cid2inchi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/cid2inchi.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_inchi.stat.csv","filename":"glycan_sequences_inchi.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.397000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000289/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000289/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e9d23d3166ac06f22f80ecbdf6a233ae","provenance_domain":{"name":"Glycan Sequences InChI","version":"v-2.1.1","created":"2019-11-13T16:26:03.109539","modified":"2023-03-14T16:02:48.680Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the sequences in InChI format and InChI key for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping dataset (https://data.glygen.org/GLY_000305). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). InChI sequences and keys are retrieved from the PubChem ftp site (ftp://ftp.ncbi.nlm.nih.gov/pubchem/Compound/CURRENT-Full/SDF/)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","InChI","PubChem"],"platform":[],"pipeline_steps":[{"name":"dataset-maker/pubchem-download-step1.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The GlyTouCan to PubChem CID mapping file was used download sdf PubChem compound files from the PubChem CID ftp site. Python scripts were used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."},{"step_number":2,"name":"pubchem-download-step2.py","description":"","prerequisite":[],"input_list":[{"uri":""}],"output_list":[{"uri":""}]},{"step_number":3,"name":"pubchem-download-step3.py","description":"","prerequisite":[],"input_list":[{"uri":""}],"output_list":[{"uri":""}]},{"step_number":4,"name":"pubchem-download-step4.py","description":"","prerequisite":[],"input_list":[{"uri":""}],"output_list":[{"uri":""}]},{"step_number":5,"name":"make-species-agnostic-dataset.py","description":"","prerequisite":[],"input_list":[{"uri":""}],"output_list":[{"uri":""}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"cid2inchi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/cid2inchi.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_inchi.stat.csv","filename":"glycan_sequences_inchi.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"InChI Sequence format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:21:52.230000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000290/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000290/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"104617ce85f501cc7b3cb93e55ddeaf36d834b7bbb5ed64f8f07094563abe246","provenance_domain":{"name":"Glycan Sequences IUPAC Extended","version":"v-0.0.0","created":"2019-11-13T16:31:31.525156","modified":"2024-05-17T11:23:55.178Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Extended"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_iupac_extended.csv","filename":"glycan_sequences_iupac_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_iupac_extended.stat.csv","filename":"glycan_sequences_iupac_extended.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Extended format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":279,"last_update":"2024-05-17T11:23:55.178455Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000290/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000290/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Extended format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences IUPAC Extended","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:31:31.525156","modified":"2022-09-26T09:04:47.893381","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Extended"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/iupac_extended.zip","filename":"iupac_extended.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_sequences_iupac_extended.csv","filename":"glycan_sequences_iupac_extended.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"ef36a7780d44d37674ef70888042cecd618b27f6bf67e07483161205e39d8e56","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_iupac_extended.csv","filename":"glycan_sequences_iupac_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_iupac_extended.stat.csv","filename":"glycan_sequences_iupac_extended.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.923000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000290/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000290/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f13724c45f2bdab9a5dd9426aced976b","provenance_domain":{"name":"Glycan Sequences IUPAC Extended","version":"v-2.1.1","created":"2019-11-13T16:31:31.525156","modified":"2022-10-12T16:36:30.995Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Extended"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/monocomp.tsv","filename":"monocomp.tsv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/iupac_extended.zip","filename":"iupac_extended.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_sequences_iupac_extended.csv","filename":"glycan_sequences_iupac_extended.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_iupac_extended.csv","filename":"glycan_sequences_iupac_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_iupac_extended.stat.csv","filename":"glycan_sequences_iupac_extended.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Extended format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:07:32.827000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000291/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000291/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SMILES Isomeric sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences SMILES Isomeric","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T16:37:56.677676","modified":"2024-05-17T11:23:55.214Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SMILES Isomeric"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"etag":"897cc9a4881eb622e04b9effe88ffe45ba2242e756612d87800ef27435316408","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_smiles_isomeric.csv","filename":"glycan_sequences_smiles_isomeric.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_smiles_isomeric.stat.csv","filename":"glycan_sequences_smiles_isomeric.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":362,"last_update":"2024-05-17T11:23:55.214297Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000291/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000291/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SMILES Isomeric sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences SMILES Isomeric","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:37:56.677676","modified":"2022-09-26T09:04:47.904121","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SMILES Isomeric"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/CID-SMILES_2020_04_29_15_19_03.gz","filename":"CID-SMILES_2020_04_29_15_19_03.gz"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_sequences_smiles_isomeric.csv","filename":"glycan_sequences_smiles_isomeric.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"etag":"0aa66a457228c18b1f1211c709b11329dd995b491bd819b2e3945bbce1db957d","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_smiles_isomeric.csv","filename":"glycan_sequences_smiles_isomeric.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_smiles_isomeric.stat.csv","filename":"glycan_sequences_smiles_isomeric.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.625000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000291/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000291/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SMILES Isomeric sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences SMILES Isomeric","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T16:37:56.677676","modified":"2022-09-26T09:04:47.904121","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SMILES Isomeric"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/CID-SMILES_2020_04_29_15_19_03.gz","filename":"CID-SMILES_2020_04_29_15_19_03.gz"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_sequences_smiles_isomeric.csv","filename":"glycan_sequences_smiles_isomeric.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"etag":"29d19a39d11ce50aafd201fb4931f8fb","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_smiles_isomeric.csv","filename":"glycan_sequences_smiles_isomeric.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_smiles_isomeric.stat.csv","filename":"glycan_sequences_smiles_isomeric.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:15.720000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000292/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000292/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"98a9db42b95e71ae3234f6b87511313185f89c6b524b32f2e568d3fe09ebf2e1","provenance_domain":{"name":"Glycan Sequences WURCS","version":"v-0.0.0","created":"2019-11-13T16:43:04.029210","modified":"2024-05-17T11:23:55.250Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in WURCS extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","WURCS"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_wurcs.csv","filename":"glycan_sequences_wurcs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_wurcs.stat.csv","filename":"glycan_sequences_wurcs.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"WURCS sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":279,"last_update":"2024-05-17T11:23:55.250649Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000292/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000292/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"WURCS sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences WURCS","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:43:04.029210","modified":"2022-09-26T09:04:48.010261","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","WURCS"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/wurcs.zip","filename":"wurcs.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_sequences_wurcs.csv","filename":"glycan_sequences_wurcs.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in WURCS extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"ea729f18057a79496f8e200825fe9ff619f2b1591c1e155f14269721c91d19bf","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_wurcs.csv","filename":"glycan_sequences_wurcs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_wurcs.stat.csv","filename":"glycan_sequences_wurcs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.174000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000292/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000292/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2d203f6502a3ae4490e43925f4fed48f","provenance_domain":{"name":"Glycan Sequences WURCS","version":"v-2.1.1","created":"2019-11-13T16:43:04.029210","modified":"2022-10-12T16:40:17.182Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in WURCS extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","WURCS"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/monocomp.tsv","filename":"monocomp.tsv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/wurcs.zip","filename":"wurcs.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_sequences_wurcs.csv","filename":"glycan_sequences_wurcs.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_wurcs.csv","filename":"glycan_sequences_wurcs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_wurcs.stat.csv","filename":"glycan_sequences_wurcs.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"WURCS sequence format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:07:33.214000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000294/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000294/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BCSDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref BCSDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T16:51:37.145018","modified":"2024-05-17T11:23:55.288Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","BCSDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to BCSDB ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"etag":"4a73825402318e792e1d16816d22a6adc04b8e2608f4448a78aaff0bd8b17406","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_bcsdb.csv","filename":"glycan_xref_bcsdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_bcsdb.stat.csv","filename":"glycan_xref_bcsdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":305,"last_update":"2024-05-17T11:23:55.288852Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000294/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000294/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BCSDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref BCSDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:51:37.145018","modified":"2022-09-26T09:04:47.974247","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","BCSDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/bcsdb.tsv","filename":"bcsdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_bcsdb.csv","filename":"glycan_xref_bcsdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to BCSDB ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"etag":"ec66956fff6327d4dcaf77582763f1adff89e61d5d3874ab269089575fb0ab09","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"bcsdb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/bcsdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_bcsdb.csv","filename":"glycan_xref_bcsdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_bcsdb.stat.csv","filename":"glycan_xref_bcsdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.788000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000294/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000294/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BCSDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref BCSDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T16:51:37.145018","modified":"2022-09-26T09:04:47.974247","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","BCSDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/bcsdb.tsv","filename":"bcsdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_bcsdb.csv","filename":"glycan_xref_bcsdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to BCSDB ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"etag":"9ae30a8de0bf1828544ca0a0faa38f0c","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"bcsdb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/bcsdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_bcsdb.csv","filename":"glycan_xref_bcsdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_bcsdb.stat.csv","filename":"glycan_xref_bcsdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:16.030000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000295/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000295/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CarbBanK cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CarbBank","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T16:55:11.149043","modified":"2024-05-17T11:23:55.326Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CarbBank","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to CarbBank ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.genome.jp/dbget-bin/www_bfind?carbbank"],"etag":"5af0304ff051d72e28ee36cc1435e9399a7ab863981dae8909a3d01429608488","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_carbbank.csv","filename":"glycan_xref_carbbank.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_carbbank.stat.csv","filename":"glycan_xref_carbbank.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":319,"last_update":"2024-05-17T11:23:55.326268Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000295/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000295/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CarbBanK cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CarbBank","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:55:11.149043","modified":"2022-09-26T09:04:47.994065","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CarbBank","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/carbbank.tsv","filename":"carbbank.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_carbbank.csv","filename":"glycan_xref_carbbank.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to CarbBank ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.genome.jp/dbget-bin/www_bfind?carbbank"],"etag":"2a876779af72921007e759ff4385c1356810899fa9f3d7f74512a153b33f33b7","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"carbbank.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/carbbank.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_carbbank.csv","filename":"glycan_xref_carbbank.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_carbbank.stat.csv","filename":"glycan_xref_carbbank.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.122000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000295/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000295/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CarbBanK cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CarbBank","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T16:55:11.149043","modified":"2022-09-26T09:04:47.994065","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CarbBank","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/carbbank.tsv","filename":"carbbank.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_carbbank.csv","filename":"glycan_xref_carbbank.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to CarbBank ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.genome.jp/dbget-bin/www_bfind?carbbank"],"etag":"9b832abd49ad517c05cc133d5d9e5a32","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"carbbank.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/carbbank.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_carbbank.csv","filename":"glycan_xref_carbbank.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_carbbank.stat.csv","filename":"glycan_xref_carbbank.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:16.225000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000296/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000296/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EBI-ChEBI","contribution":["contributedBy"],"name":"Gareth Owen","email":"gowen@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T16:58:52.830892","modified":"2024-05-17T11:23:55.366Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file (database_accession) was downloaded directly from the CHEBI-EBI FTP dowloads (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The following rules were applied to generate the final output file: 1) rows where \"SOURCE\" column = GlyTouCan were filtered out. 2) for such rows  \"COMPOUND_ID\" is chebi_id and \"ACCESSION_NUMBER\" is glytoucan_ac. 2) the extracted glytoucan_ac were checked against the GlyGen glycan masterlist (https://data.glygen.org/GLY_000281 or input file glycan_masterlist.csv) and the GlyTouCan accessions not included in the GlyGen glycan masterlist were excluded to generate the final output file. The glycans are submitted into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[" The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession). The mapping is produced using the direct download files(database_accession.tsv) from the ChEBI-EBI FTP (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The glycans are mapped/registered into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."],"etag":"ac957a45da24a59449b3366631f0a4ae90f342ec5a966d96ee8e0699dfc9e3bc","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_chebi.stat.csv","filename":"glycan_xref_chebi.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":751,"last_update":"2024-05-17T11:23:55.366256Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000296/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000296/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EBI-ChEBI","contribution":["contributedBy"],"name":"Gareth Owen","email":"gowen@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T16:58:52.830892","modified":"2022-09-26T09:04:47.924861","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/database_accession.tsv","filename":"database_accession.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}],"prerequisite":[],"description":"The input file (database_accession) was downloaded directly from the CHEBI-EBI FTP dowloads (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The following rules were applied to generate the final output file: 1) rows where \"SOURCE\" column = GlyTouCan were filtered out. 2) for such rows  \"COMPOUND_ID\" is chebi_id and \"ACCESSION_NUMBER\" is glytoucan_ac. 2) the extracted glytoucan_ac were checked against the GlyGen glycan masterlist (https://data.glygen.org/GLY_000281 or input file glycan_masterlist.csv) and the GlyTouCan accessions not included in the GlyGen glycan masterlist were excluded to generate the final output file. The glycans are submitted into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[" The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession). The mapping is produced using the direct download files(database_accession.tsv) from the ChEBI-EBI FTP (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The glycans are mapped/registered into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."],"etag":"6f6c21b31f8b1965cb1755930f4bddd9ba6fe69cdf0450bac1713328b13cb745","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"database_accession.tsv","uri":"https:/data.glygen.org/ln2downloads/chebi/07_16_2021/database_accession.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_chebi.stat.csv","filename":"glycan_xref_chebi.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.522000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000296/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000296/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EBI-ChEBI","contribution":["contributedBy"],"name":"Gareth Owen","email":"gowen@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T16:58:52.830892","modified":"2022-09-26T09:04:47.924861","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/database_accession.tsv","filename":"database_accession.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}],"prerequisite":[],"description":"The input file (database_accession) was downloaded directly from the CHEBI-EBI FTP dowloads (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The following rules were applied to generate the final output file: 1) rows where \"SOURCE\" column = GlyTouCan were filtered out. 2) for such rows  \"COMPOUND_ID\" is chebi_id and \"ACCESSION_NUMBER\" is glytoucan_ac. 2) the extracted glytoucan_ac were checked against the GlyGen glycan masterlist (https://data.glygen.org/GLY_000281 or input file glycan_masterlist.csv) and the GlyTouCan accessions not included in the GlyGen glycan masterlist were excluded to generate the final output file. The glycans are submitted into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[" The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession). The mapping is produced using the direct download files(database_accession.tsv) from the ChEBI-EBI FTP (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The glycans are mapped/registered into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."],"etag":"1360a34a50afafc6b09aedea6e75cee0","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"database_accession.tsv","uri":"/data/shared/glyds/downloads/chebi/2023_05_19/database_accession.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_chebi.stat.csv","filename":"glycan_xref_chebi.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:16.420000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000298/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000298/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CFG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CFG","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-13T17:22:49.976947","modified":"2024-05-17T11:23:55.404Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CFG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to CFG ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.functionalglycomics.org/"],"etag":"a706435d9eae944290acd1b6fd21f3881344fb73ea8ab905d9af86729e7fb323","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_cfg.csv","filename":"glycan_xref_cfg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_cfg.stat.csv","filename":"glycan_xref_cfg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":299,"last_update":"2024-05-17T11:23:55.404316Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000298/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000298/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CFG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CFG","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-13T17:22:49.976947","modified":"2022-09-26T09:04:47.979559","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CFG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/cfg.tsv","filename":"cfg.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_cfg.csv","filename":"glycan_xref_cfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to CFG ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.functionalglycomics.org/"],"etag":"0e4e5cc001fcec478aecb88548cf0cf4f9e26d72ddf38eac41a19040889c1943","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"cfg.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/cfg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_cfg.csv","filename":"glycan_xref_cfg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_cfg.stat.csv","filename":"glycan_xref_cfg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.064000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000298/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000298/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CFG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CFG","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-13T17:22:49.976947","modified":"2022-09-26T09:04:47.979559","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CFG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/cfg.tsv","filename":"cfg.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_cfg.csv","filename":"glycan_xref_cfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to CFG ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.functionalglycomics.org/"],"etag":"da086db8cdc0c5ed7fbd11dd088f976e","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"cfg.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/cfg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_cfg.csv","filename":"glycan_xref_cfg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_cfg.stat.csv","filename":"glycan_xref_cfg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:16.616000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000301/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000301/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyConnect cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyConnect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T11:18:37.879581","modified":"2024-05-17T11:23:55.443Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyConnect","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlyConnect ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;https://glyconnect.expasy.org"],"etag":"7b1ed04e2ffcfbe107a958152dda6c3ae94b9f383da510e62b86710f4e30577b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glyconnect.csv","filename":"glycan_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glyconnect.stat.csv","filename":"glycan_xref_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":327,"last_update":"2024-05-17T11:23:55.443674Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000301/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000301/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyConnect cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyConnect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T11:18:37.879581","modified":"2022-09-26T09:05:27.617020","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyConnect","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glyconnect","filename":"glyconnect"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_glyconnect.csv","filename":"glycan_xref_glyconnect.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlyConnect ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;https://glyconnect.expasy.org"],"etag":"06d4e2e44288f055551ac666e5edeb111b1a3f7429c5629c7fbbca97fb59c400","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glyconnect.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/glyconnect.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glyconnect.csv","filename":"glycan_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glyconnect.stat.csv","filename":"glycan_xref_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.488000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000301/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000301/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyConnect cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyConnect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T11:18:37.879581","modified":"2022-09-26T09:05:27.617020","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyConnect","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glyconnect","filename":"glyconnect"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_glyconnect.csv","filename":"glycan_xref_glyconnect.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlyConnect ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;https://glyconnect.expasy.org"],"etag":"a531e5c965c8bca969dcd354f1698eb8","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glyconnect.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/glyconnect.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glyconnect.csv","filename":"glycan_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glyconnect.stat.csv","filename":"glycan_xref_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:16.807000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000302/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000302/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosciences.de","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Glycosciences.de","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T11:26:24.134158","modified":"2024-05-17T11:23:55.480Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosciences.de","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GLYCOSCIENCES.DE ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;http://www.glycosciences.de/"],"etag":"0b71469a9af18f8a722a2f3bd1244d1bfa6c58224b3b93c46dcca921666224ba","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glycosciencesde.csv","filename":"glycan_xref_glycosciencesde.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glycosciencesde.stat.csv","filename":"glycan_xref_glycosciencesde.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":332,"last_update":"2024-05-17T11:23:55.480843Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000302/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000302/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosciences.de","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Glycosciences.de","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T11:26:24.134158","modified":"2022-09-26T09:05:27.740092","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosciences.de","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_glycosciencesde.csv","filename":"glycan_xref_glycosciencesde.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GLYCOSCIENCES.DE ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;http://www.glycosciences.de/"],"etag":"8c2473e50d92a4c1fc08256fd124eb6f50d1c7234ea9cba31870e94a9045c684","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycosciencesde.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/glycosciencesde.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glycosciencesde.csv","filename":"glycan_xref_glycosciencesde.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glycosciencesde.stat.csv","filename":"glycan_xref_glycosciencesde.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.774000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000302/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000302/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosciences.de","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Glycosciences.de","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T11:26:24.134158","modified":"2022-09-26T09:05:27.740092","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosciences.de","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_glycosciencesde.csv","filename":"glycan_xref_glycosciencesde.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GLYCOSCIENCES.DE ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;http://www.glycosciences.de/"],"etag":"ee8e00eb64bc114eb23375401e965494","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycosciencesde.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/glycosciencesde.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glycosciencesde.csv","filename":"glycan_xref_glycosciencesde.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glycosciencesde.stat.csv","filename":"glycan_xref_glycosciencesde.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:16.995000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000303/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000303/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"KEGG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref KEGG","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T11:31:22.083466","modified":"2024-05-17T11:23:55.519Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","KEGG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to KEGG glycan ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.genome.jp/kegg/glycan/"],"etag":"d1ca7b4d2aa8f1baad1923675d3389ffd1efa52db6d87eee35cac364080feed8","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_kegg.stat.csv","filename":"glycan_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":334,"last_update":"2024-05-17T11:23:55.519743Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000303/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000303/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"KEGG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref KEGG","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T11:31:22.083466","modified":"2022-09-26T09:05:27.766297","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","KEGG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/kegg.tsv","filename":"kegg.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to KEGG glycan ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.genome.jp/kegg/glycan/"],"etag":"cf00ceb37514bc8985cd1d897ac32f0ffe9ffc7691857b94712625d184c851fe","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"kegg.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/kegg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_kegg.stat.csv","filename":"glycan_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.322000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000303/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000303/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"KEGG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref KEGG","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T11:31:22.083466","modified":"2022-09-26T09:05:27.766297","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","KEGG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/kegg.tsv","filename":"kegg.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to KEGG glycan ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.genome.jp/kegg/glycan/"],"etag":"ff0725ba131a605b257263c4f71ec025","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"kegg.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/kegg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_kegg.stat.csv","filename":"glycan_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:17.181000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000304/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000304/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T11:38:02.465398","modified":"2024-05-17T11:23:55.556Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"etag":"16bc38d8a2bcd1fb6cbdaa657ba5048cf69fc97551166d838262c960267c1a68","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_pdb.csv","filename":"glycan_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_pdb.stat.csv","filename":"glycan_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-05-17T11:23:55.556632Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000304/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000304/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T11:38:02.465398","modified":"2022-09-26T09:05:27.674247","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/pdb.tsv","filename":"pdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_pdb.csv","filename":"glycan_xref_pdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"etag":"90b51328fd233788567cd8d7981677edd1e114718397ebdd79cc20cd11cff722","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"pdb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/pdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pdb.csv","filename":"glycan_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pdb.stat.csv","filename":"glycan_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.063000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000304/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000304/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T11:38:02.465398","modified":"2022-09-26T09:05:27.674247","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/pdb.tsv","filename":"pdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_pdb.csv","filename":"glycan_xref_pdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"etag":"20a8fce5670616df4fcccd0e2b7fdb69","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"pdb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/pdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pdb.csv","filename":"glycan_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pdb.stat.csv","filename":"glycan_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:17.370000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000305/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000305/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PubChem","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T11:47:20.058924","modified":"2024-05-17T11:23:55.595Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov"],"etag":"6c838c2c2297e256f74468cfe5c736411596724f3c613312f8e7a243e2e83912","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_pubchem.stat.csv","filename":"glycan_xref_pubchem.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-17T11:23:55.595646Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000305/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000305/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PubChem","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T11:47:20.058924","modified":"2022-09-26T09:05:27.731017","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/pbch.tsv","filename":"pbch.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov"],"etag":"1dd620fb6e388e1a4c6aa1029b1ac40a15d57590b517fd9107e3f0546b69344a","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"pbch.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/pbch.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.stat.csv","filename":"glycan_xref_pubchem.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.405000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000305/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000305/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PubChem","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T11:47:20.058924","modified":"2022-09-26T09:05:27.731017","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/pbch.tsv","filename":"pbch.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov"],"etag":"17ef925bab44b2d23c97b5c1c016808e","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"pbch.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/pbch.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.stat.csv","filename":"glycan_xref_pubchem.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:17.554000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000306/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000306/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T11:57:23.383521","modified":"2024-05-17T11:23:55.634Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to UniCarbDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://unicarb-db.expasy.org/"],"etag":"c10df837f8300f7d32810d20228ebf64bb7e20971891272fca01a40daeb6ff59","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_unicarbdb.csv","filename":"glycan_xref_unicarbdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_unicarbdb.stat.csv","filename":"glycan_xref_unicarbdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":328,"last_update":"2024-05-17T11:23:55.634224Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000306/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000306/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T11:57:23.383521","modified":"2022-09-26T09:05:27.641688","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_unicarbdb.csv","filename":"glycan_xref_unicarbdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to UniCarbDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://unicarb-db.expasy.org/"],"etag":"845d2b6fdc66b3849dbb364dfbea589dec8e5802658560e941040cf07697251c","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"unicarbdb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/unicarbdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_unicarbdb.csv","filename":"glycan_xref_unicarbdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_unicarbdb.stat.csv","filename":"glycan_xref_unicarbdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.908000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000306/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000306/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T11:57:23.383521","modified":"2022-09-26T09:05:27.641688","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_unicarbdb.csv","filename":"glycan_xref_unicarbdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to UniCarbDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://unicarb-db.expasy.org/"],"etag":"762467fc742d84eb23ee69deb94da7ad","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"unicarbdb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/unicarbdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_unicarbdb.csv","filename":"glycan_xref_unicarbdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_unicarbdb.stat.csv","filename":"glycan_xref_unicarbdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:17.742000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000307/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000307/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbKB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T12:09:00.597068","modified":"2024-05-17T11:23:55.673Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbKB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to UniCarbKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; http://www.unicarbkb.org/"],"etag":"c8f6a81bb4501d3aa7a02295b4c03ac2b2cd233a9abe966406e68db0c8e47965","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_unicarbkb.stat.csv","filename":"glycan_xref_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":323,"last_update":"2024-05-17T11:23:55.673792Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000307/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000307/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbKB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T12:09:00.597068","modified":"2022-09-26T09:05:27.664167","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbKB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to UniCarbKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; http://www.unicarbkb.org/"],"etag":"924236872b6f28352a30b72e6249333ea79c8092411144affc012dd109e94382","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"unicarbkb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/unicarbkb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_unicarbkb.stat.csv","filename":"glycan_xref_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.986000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000307/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000307/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbKB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T12:09:00.597068","modified":"2022-09-26T09:05:27.664167","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbKB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to UniCarbKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; http://www.unicarbkb.org/"],"etag":"e5255bc2492e8443ab8f9d4582b4b0ca","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"unicarbkb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/unicarbkb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_unicarbkb.stat.csv","filename":"glycan_xref_unicarbkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:17.938000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000308/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000308/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Genomics England- Congenital Disorders of Glycosylation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T12:15:32.954297","modified":"2024-05-17T11:23:55.712Z","version":"v-0.0.0"},"description_domain":{"keywords":["Protein","UniProtKB Accession","Genomics England","Panel App"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the Genomics England (https://panelapp.genomicsengland.co.uk/panels/25/) from panel \"Congenital disorders of glycosylation\". A python script was used to process the data. 1. Map the HGNC/gene symbol to UniProtKB canonical accessions from the GlyGen protein masterlist. 2. Only those gene-disease associations are considered where one of the source is \"Expert Review Green\". 3. The MIM ID (Mendelian Inheritance ID) from column \"Phenotypes\" is mapped to DOID (Disease Ontology ID) using input file 2."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"/make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides Genes involved in the Congenital disorders of glycosylation from Genomics England PanelApp ( PanelApp crowdsources expert knowledge to establish consensus diagnostic gene panels. Antonio Rueda Martin and Eleanor Williams, Rebecca E. Foulger, Sarah Leigh, Louise C. Daugherty, Olivia Niblock, Ivone U. S. Leong, Katherine R. Smith, Oleg Gerasimenko, Eik Haraldsdottir, Ellen Thomas, Richard H. Scott, Emma Baple, Arianna Tucci, Helen Brittain, Anna de Burca, Kristina Ibañez, Dalia Kasperaviciute, Damian Smedley, Mark Caulfield, Augusto Rendon & Ellen M. McDonagh. Nat Genet (2019) doi:10.1038/s41588-019-0528-2)"],"etag":"f6df84d7cd7e3aa9f5dd1490005c31b88e07fe1594592150cc0bea1ed864c9d9","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_genomics_england.csv","filename":"human_protein_disease_genomics_england.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_genomics_england.stat.csv","filename":"human_protein_disease_genomics_england.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":633,"last_update":"2024-05-17T11:23:55.712028Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000308/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000308/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Genomics England- Congenital Disorders of Glycosylation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T12:15:32.954297","modified":"2022-09-26T09:05:27.690344","version":"v-2.0.2"},"description_domain":{"keywords":["Protein","UniProtKB Accession","Genomics England","Panel App"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/congenital_disorders_of_glycosylation.tsv","filename":"congenital_disorders_of_glycosylation.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviwed/protein_domap.csv","filename":"protein_domap.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_genomics_england_disease.csv","filename":"human_protein_genomics_england_disease.csv"}],"prerequisite":[],"description":"The input file was downloaded from the Genomics England (https://panelapp.genomicsengland.co.uk/panels/25/) from panel \"Congenital disorders of glycosylation\". A python script was used to process the data. 1. Map the HGNC/gene symbol to UniProtKB canonical accessions from the GlyGen protein masterlist. 2. Only those gene-disease associations are considered where one of the source is \"Expert Review Green\". 3. The MIM ID (Mendelian Inheritance ID) from column \"Phenotypes\" is mapped to DOID (Disease Ontology ID) using input file 2."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"/make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides Genes involved in the Congenital disorders of glycosylation from Genomics England PanelApp ( PanelApp crowdsources expert knowledge to establish consensus diagnostic gene panels. Antonio Rueda Martin and Eleanor Williams, Rebecca E. Foulger, Sarah Leigh, Louise C. Daugherty, Olivia Niblock, Ivone U. S. Leong, Katherine R. Smith, Oleg Gerasimenko, Eik Haraldsdottir, Ellen Thomas, Richard H. Scott, Emma Baple, Arianna Tucci, Helen Brittain, Anna de Burca, Kristina Ibañez, Dalia Kasperaviciute, Damian Smedley, Mark Caulfield, Augusto Rendon & Ellen M. McDonagh. Nat Genet (2019) doi:10.1038/s41588-019-0528-2)"],"etag":"c6b01a12878a0652521cf58627212b0b2682972a728ada18559fd49ee472a6dc","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_hgnc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_hgnc.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"congenital_disorders_of_glycosylation.tsv","uri":"https:/data.glygen.org/ln2downloads/genomics_england/07_16_2021/congenital_disorders_of_glycosylation.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_genomics_england.csv","filename":"human_protein_disease_genomics_england.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_genomics_england.stat.csv","filename":"human_protein_disease_genomics_england.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.509000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000308/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000308/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Genomics England- Congenital Disorders of Glycosylation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T12:15:32.954297","modified":"2022-09-26T09:05:27.690344","version":"v-2.1.1"},"description_domain":{"keywords":["Protein","UniProtKB Accession","Genomics England","Panel App"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/congenital_disorders_of_glycosylation.tsv","filename":"congenital_disorders_of_glycosylation.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviwed/protein_domap.csv","filename":"protein_domap.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_genomics_england_disease.csv","filename":"human_protein_genomics_england_disease.csv"}],"prerequisite":[],"description":"The input file was downloaded from the Genomics England (https://panelapp.genomicsengland.co.uk/panels/25/) from panel \"Congenital disorders of glycosylation\". A python script was used to process the data. 1. Map the HGNC/gene symbol to UniProtKB canonical accessions from the GlyGen protein masterlist. 2. Only those gene-disease associations are considered where one of the source is \"Expert Review Green\". 3. The MIM ID (Mendelian Inheritance ID) from column \"Phenotypes\" is mapped to DOID (Disease Ontology ID) using input file 2."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"/make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides Genes involved in the Congenital disorders of glycosylation from Genomics England PanelApp ( PanelApp crowdsources expert knowledge to establish consensus diagnostic gene panels. Antonio Rueda Martin and Eleanor Williams, Rebecca E. Foulger, Sarah Leigh, Louise C. Daugherty, Olivia Niblock, Ivone U. S. Leong, Katherine R. Smith, Oleg Gerasimenko, Eik Haraldsdottir, Ellen Thomas, Richard H. Scott, Emma Baple, Arianna Tucci, Helen Brittain, Anna de Burca, Kristina Ibañez, Dalia Kasperaviciute, Damian Smedley, Mark Caulfield, Augusto Rendon & Ellen M. McDonagh. Nat Genet (2019) doi:10.1038/s41588-019-0528-2)"],"etag":"ac5a2eeb188204a5c87af4da272d8dc8","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_hgnc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"congenital_disorders_of_glycosylation.tsv","uri":"/data/shared/glyds/downloads/genomics_england/2023_05_18/congenital_disorders_of_glycosylation.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_genomics_england.csv","filename":"human_protein_disease_genomics_england.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_genomics_england.stat.csv","filename":"human_protein_disease_genomics_england.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:18.128000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000309/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000309/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"synthesized Glycan","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Synthesized glycans","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Gerardus JOSEPHUS Boons","email":"gjboons@ccrc.uga.edu"},{"affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Lin Liu","email":"linliu@ccrc.uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-14T15:24:17.374565","modified":"2024-05-17T11:23:55.750Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Synthesized Glycan","ID/Accession Mapping"],"pipeline_steps":[{"name":"manual","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"Authors provided figures for  fully-defined glycan strutures (images) long with the associated publication (PubMed ID). Based on the images, the glycans were mapped or registered in the GlyTouCan database manually. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset lists the synthesized glycans which are identified by the the GlyTouCan accessions. Source:- The Boons Group. https://www.ccrc.uga.edu/~gjboons/boons/Home.htm()"],"etag":"2ea5c68c51a002f3536ba15e28cce3aa14781b09140e468f326e8b0275d112bd","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_synthesized.csv","filename":"glycan_synthesized.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_synthesized.stat.csv","filename":"glycan_synthesized.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":172,"last_update":"2024-05-17T11:23:55.750210Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000309/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000309/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"synthesized Glycan","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Synthesized glycans","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Gerardus JOSEPHUS Boons","email":"gjboons@ccrc.uga.edu"},{"affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Lin Liu","email":"linliu@ccrc.uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-14T15:24:17.374565","modified":"2022-09-26T09:05:27.718160","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Synthesized Glycan","ID/Accession Mapping"],"pipeline_steps":[{"name":"manual","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_synthesized.csv","filename":"glycan_synthesized.csv"}],"prerequisite":[],"description":"Authors provided figures for  fully-defined glycan strutures (images) long with the associated publication (PubMed ID). Based on the images, the glycans were mapped or registered in the GlyTouCan database manually. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset lists the synthesized glycans which are identified by the the GlyTouCan accessions. Source:- The Boons Group. https://www.ccrc.uga.edu/~gjboons/boons/Home.htm()"],"etag":"5b4c456b5e0c03ca6b955367d49d56109a8ca629b98e3abd16733d29c79b97c5","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_synthesized.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycan_synthesized.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_synthesized.csv","filename":"glycan_synthesized.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_synthesized.stat.csv","filename":"glycan_synthesized.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.241000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000309/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000309/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"synthesized Glycan","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Synthesized glycans","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Gerardus JOSEPHUS Boons","email":"gjboons@ccrc.uga.edu"},{"affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Lin Liu","email":"linliu@ccrc.uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-14T15:24:17.374565","modified":"2022-09-26T09:05:27.718160","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Synthesized Glycan","ID/Accession Mapping"],"pipeline_steps":[{"name":"manual","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_synthesized.csv","filename":"glycan_synthesized.csv"}],"prerequisite":[],"description":"Authors provided figures for  fully-defined glycan strutures (images) long with the associated publication (PubMed ID). Based on the images, the glycans were mapped or registered in the GlyTouCan database manually. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset lists the synthesized glycans which are identified by the the GlyTouCan accessions. Source:- The Boons Group. https://www.ccrc.uga.edu/~gjboons/boons/Home.htm()"],"etag":"e951049049744a982fb377dd6cebce98","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_synthesized.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycan_synthesized.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_synthesized.csv","filename":"glycan_synthesized.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_synthesized.stat.csv","filename":"glycan_synthesized.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:18.317000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000310/DRAFT","contents":{"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_reactome.stat.csv","filename":"human_protein_citations_reactome.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T12:49:42.900057","modified":"2024-05-17T11:23:55.788Z","version":"v-0.0.0","name":"Human Protein Citations (Reactome)"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for Homo sapiens [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"object_id":"https://biocomputeobject.org/GLY_000310/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"49601c8df20da05b3967638098f96a5d7e2aa90788d19bdfa8c77991476cc1fb"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":327,"last_update":"2024-05-17T11:23:55.788516Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000310/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"human_protein_reactions_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_reactions_reactome.csv"}},{"uri":{"filename":"human_protein_xref_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_reactome.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_reactome.stat.csv","filename":"human_protein_citations_reactome.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T12:49:42.900057","modified":"2022-09-26T09:05:27.638299","version":"v-2.0.2","name":"Human Protein Citations (Reactome)"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for human [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"object_id":"https://biocomputeobject.org/GLY_000310/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"459fe990c25e989c7b12eeeb32b73278f062636b4dfaede6bb8907c153c4b810"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.534000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000310/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"human_protein_reactions_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_reactions_reactome.csv"}},{"uri":{"filename":"human_protein_xref_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_reactome.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_reactome.stat.csv","filename":"human_protein_citations_reactome.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T12:49:42.900057","modified":"2022-09-26T09:05:27.638299","version":"v-2.1.1","name":"Human Protein Citations (Reactome)"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for human [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"object_id":"https://biocomputeobject.org/GLY_000310/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"67e0b063fe40f0efb49f4974a58c4b88"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:18.506000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000313/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000313/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T13:05:58.133075","modified":"2024-05-17T11:23:55.825Z","version":"v-0.0.0"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Binary Interaction (IntAct) dataset contains Homo sapiens [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"f68f217073ec99593d60516542c2236519d222aef3922efc202067c3b07daeaa","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_binary_interactions.csv","filename":"human_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_binary_interactions.stat.csv","filename":"human_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2024-05-17T11:23:55.825891Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000313/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000313/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T13:05:58.133075","modified":"2022-09-26T09:05:27.726213","version":"v-2.0.2"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_binary_interactions.csv","filename":"human_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Binary Interaction (IntAct) dataset contains human [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"24cab6cb005896a0192437bbeaeb320af41439f997497bf8b7a8ea2a80e67664","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_binary_interactions.csv","filename":"human_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_binary_interactions.stat.csv","filename":"human_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.136000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000313/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000313/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T13:05:58.133075","modified":"2022-09-26T09:05:27.726213","version":"v-2.1.1"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_binary_interactions.csv","filename":"human_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Binary Interaction (IntAct) dataset contains human [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"f016f68345832d8e15f4eefd67cfda07","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_binary_interactions.csv","filename":"human_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_binary_interactions.stat.csv","filename":"human_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:18.698000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000314/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000314/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T13:08:44.669121","modified":"2024-05-17T11:23:55.863Z","version":"v-0.0.0"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Binary Interaction (IntAct) dataset contains Mus musculus [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"2d91bce4c46f55b081a9b87bca69d28614eea39f9f70a32462a12c8e0843d30a","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_binary_interactions.csv","filename":"mouse_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_binary_interactions.stat.csv","filename":"mouse_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2024-05-17T11:23:55.863349Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000314/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000314/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T13:08:44.669121","modified":"2022-09-26T09:05:27.742299","version":"v-2.0.2"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_binary_interactions.csv","filename":"mouse_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Binary Interaction (IntAct) dataset contains mouse [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"98fa61b73e91028417055e46dad335fe68202e04c702d4db9fed1bad4b4e5579","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_binary_interactions.csv","filename":"mouse_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_binary_interactions.stat.csv","filename":"mouse_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.136000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000314/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000314/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T13:08:44.669121","modified":"2022-09-26T09:05:27.742299","version":"v-2.1.1"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_binary_interactions.csv","filename":"mouse_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Binary Interaction (IntAct) dataset contains mouse [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"c3d7b149af3df6298ac5beb973b3fad6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_binary_interactions.csv","filename":"mouse_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_binary_interactions.stat.csv","filename":"mouse_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:18.885000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000315/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000315/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T13:10:44.152278","modified":"2024-05-17T11:23:55.901Z","version":"v-0.0.0"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Binary Interaction (IntAct) dataset contains Rattus norvegicus [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"60d4d164de30f977330012768e73c9c130fe5ca4ecf09867e91adea1dd6915bd","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_binary_interactions.csv","filename":"rat_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_binary_interactions.stat.csv","filename":"rat_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":393,"last_update":"2024-05-17T11:23:55.901063Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000315/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000315/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T13:10:44.152278","modified":"2022-09-26T09:05:27.760577","version":"v-2.0.2"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_binary_interactions.csv","filename":"rat_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Binary Interaction (IntAct) dataset contains rat [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"1ca027d4669552829237195d580be50dc353e9ab126759e8155b93159c5a9cef","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_binary_interactions.csv","filename":"rat_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_binary_interactions.stat.csv","filename":"rat_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.743000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000315/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000315/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T13:10:44.152278","modified":"2022-09-26T09:05:27.760577","version":"v-2.1.1"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_binary_interactions.csv","filename":"rat_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Binary Interaction (IntAct) dataset contains rat [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"8d63ba268e81e67da2741caa36e0a958","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_binary_interactions.csv","filename":"rat_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_binary_interactions.stat.csv","filename":"rat_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:19.072000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000316/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000316/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T13:58:37.032006","modified":"2024-06-03T20:37:26.998Z","version":"v-0.0.0"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein PTM Annotation (UniProtKB) dataset contains Homo sapiens [taxid:9606] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"c63c245900d7041dd3044470b0a744bceebffd160e3fbdcaec818b1e9abdc767","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_ptm_annotation_uniprotkb.csv","filename":"human_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_ptm_annotation_uniprotkb.stat.csv","filename":"human_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":311,"last_update":"2024-06-03T20:37:26.998166Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000316/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000316/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T13:58:37.032006","modified":"2022-09-26T09:05:27.611063","version":"v-2.0.2"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_ptm_annotation_uniprotkb.csv","filename":"human_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein PTM Annotation (UniProtKB) dataset contains human [taxid:9606] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"7ad96178b0a61306ea746aa43fc0ef3c84b27d9514e1dfb4155bb9e3c43cb834","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_ptm_annotation_uniprotkb.csv","filename":"human_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_ptm_annotation_uniprotkb.stat.csv","filename":"human_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.383000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000316/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000316/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T13:58:37.032006","modified":"2022-09-26T09:05:27.611063","version":"v-2.1.1"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_ptm_annotation_uniprotkb.csv","filename":"human_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein PTM Annotation (UniProtKB) dataset contains human [taxid:9606] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"a434e1a9adb0782aaffb0e694beb2490","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_ptm_annotation_uniprotkb.csv","filename":"human_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_ptm_annotation_uniprotkb.stat.csv","filename":"human_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:19.257000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000317/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000317/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T14:05:28.986536","modified":"2024-06-03T20:37:49.852Z","version":"v-0.0.0"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein PTM Annotation (UniProtKB) dataset contains Mus musculus [taxid:10090] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"bf2753eeb98fef6d846f71a17caf27094577c270ea39a89a97f5c5f155d96748","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_ptm_annotation_uniprotkb.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_ptm_annotation_uniprotkb.stat.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-06-03T20:37:49.852636Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000317/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000317/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T14:05:28.986536","modified":"2022-09-26T09:05:27.622846","version":"v-2.0.2"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_ptm_annotation_uniprotkb.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein PTM Annotation (UniProtKB) dataset contains mouse [taxid:10090] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"fe18c55f71830ad587452d9414654c33a7e31ddb85fa445eb7182aac12c80ba0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_ptm_annotation_uniprotkb.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_ptm_annotation_uniprotkb.stat.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.124000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000317/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000317/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T14:05:28.986536","modified":"2022-09-26T09:05:27.622846","version":"v-2.1.1"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_ptm_annotation_uniprotkb.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein PTM Annotation (UniProtKB) dataset contains mouse [taxid:10090] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"77ba71ff2e9e751e05eff04a2711b010","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_ptm_annotation_uniprotkb.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_ptm_annotation_uniprotkb.stat.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:19.438000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000318/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000318/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T14:07:14.445471","modified":"2024-06-03T20:38:10.236Z","version":"v-0.0.0"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein PTM Annotation (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"d4e61d7103fa8b1b06f53067e2dae76720078ddddbcc565e69c9d105a068d025","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_ptm_annotation_uniprotkb.csv","filename":"rat_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_ptm_annotation_uniprotkb.stat.csv","filename":"rat_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":315,"last_update":"2024-06-03T20:38:10.235996Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000318/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000318/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T14:07:14.445471","modified":"2022-09-26T09:05:27.733591","version":"v-2.0.2"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_ptm_annotation_uniprotkb.csv","filename":"rat_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein PTM Annotation (UniProtKB) dataset contains rat [taxid:10116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"5eff8078ca2b3c08861c723da6ec04153c5ffda89616c7d8923350880db80a5c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_ptm_annotation_uniprotkb.csv","filename":"rat_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_ptm_annotation_uniprotkb.stat.csv","filename":"rat_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.912000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000318/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000318/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T14:07:14.445471","modified":"2022-09-26T09:05:27.733591","version":"v-2.1.1"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_ptm_annotation_uniprotkb.csv","filename":"rat_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein PTM Annotation (UniProtKB) dataset contains rat [taxid:10116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"8198e245e67d41b5aa19657ae50bea68","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_ptm_annotation_uniprotkb.csv","filename":"rat_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_ptm_annotation_uniprotkb.stat.csv","filename":"rat_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:19.619000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000319/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000319/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T15:03:14.488331","modified":"2024-06-03T20:52:01.756Z","version":"v-0.0.0"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Protein Reactions (Reactome) dataset contains reactions information for pathways for Mus musculus [taxid:10090] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"ecdb69928007add591c03818aabea4b6374dc439e5e64190ab5dae40bdfc4bbf","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_reactions_reactome.csv","filename":"mouse_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_reactions_reactome.stat.csv","filename":"mouse_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":329,"last_update":"2024-06-03T20:52:01.756061Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000319/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000319/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T15:03:14.488331","modified":"2022-09-26T09:05:27.774888","version":"v-2.0.2"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_reactions_reactome.csv","filename":"mouse_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Reactions (Reactome) dataset contains reactions information for pathways for mouse [taxid:10090] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"59cd645ec1a65217bfcc970cc52374cfcb3626a4521f96e24b19000ec141583c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_reactions_reactome.csv","filename":"mouse_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_reactions_reactome.stat.csv","filename":"mouse_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.278000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000319/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000319/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T15:03:14.488331","modified":"2022-09-26T09:05:27.774888","version":"v-2.1.1"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_reactions_reactome.csv","filename":"mouse_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Reactions (Reactome) dataset contains reactions information for pathways for mouse [taxid:10090] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"59a37bd722b87bacec51736abd42f7c6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_reactions_reactome.csv","filename":"mouse_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_reactions_reactome.stat.csv","filename":"mouse_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:19.801000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000320/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000320/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T15:06:36.890527","modified":"2024-05-17T11:23:56.101Z","version":"v-0.0.0"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for Homo sapiens [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"66bafcf33ab99fadd62be730d981ad8a62062bb32591b1051cc496fc98b85434","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_reactions_reactome.csv","filename":"human_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_reactions_reactome.stat.csv","filename":"human_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":327,"last_update":"2024-05-17T11:23:56.101005Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000320/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000320/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T15:06:36.890527","modified":"2022-09-26T09:05:27.602135","version":"v-2.0.2"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_reactions_reactome.csv","filename":"human_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for human [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"73b8910bfa2533749111931ffe699faabf3c1d117873a7fc1bcac10ffa141c59","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_reactions_reactome.csv","filename":"human_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_reactions_reactome.stat.csv","filename":"human_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.607000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000320/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000320/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T15:06:36.890527","modified":"2022-09-26T09:05:27.602135","version":"v-2.1.1"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_reactions_reactome.csv","filename":"human_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for human [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"23b8cfcef551bd8dadd65113f3b23403","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_reactions_reactome.csv","filename":"human_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_reactions_reactome.stat.csv","filename":"human_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:19.988000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000321/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000321/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-11-30T15:08:38.029791","modified":"2024-05-17T11:23:56.142Z","version":"v-0.0.0"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Reactions (Reactome) dataset contains reactions information for pathways for Rattus norvegicus [taxid:10116] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7e34d602b25fb218c5c42e889fb95f8d58a8ee99ba98f461bcd39e49d24c1c6b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_reactions_reactome.csv","filename":"rat_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_reactions_reactome.stat.csv","filename":"rat_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-17T11:23:56.142109Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000321/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000321/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-11-30T15:08:38.029791","modified":"2022-09-26T09:05:27.631813","version":"v-2.0.2"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_reactions_reactome.csv","filename":"rat_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Reactions (Reactome) dataset contains reactions information for pathways for rat [taxid:10116] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"b5c9a0e020cd5901f6e6579ea9bba213dedfc35c03aaafa1f68f21e8329ef454","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_reactions_reactome.csv","filename":"rat_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_reactions_reactome.stat.csv","filename":"rat_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.367000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000321/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000321/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Reactions (Reactome)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-11-30T15:08:38.029791","modified":"2022-09-26T09:05:27.631813","version":"v-2.1.1"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_reactions_reactome.csv","filename":"rat_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Reactions (Reactome) dataset contains reactions information for pathways for rat [taxid:10116] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"9b63451ac3383400770615d2614ee8c7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_reactions_reactome.csv","filename":"rat_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_reactions_reactome.stat.csv","filename":"rat_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:20.183000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000322/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000322/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-12-01T15:29:48.229274","modified":"2024-06-03T20:38:33.692Z","version":"v-0.0.0"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Site Annotation (UniProtKB) dataset contains Homo sapiens [taxid:9606] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"ade945b28c2cd5bc0886f558ad935862637e77ea89e6a78b068ebfb267620a1b","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_site_annotation_uniprotkb.csv","filename":"human_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_site_annotation_uniprotkb.stat.csv","filename":"human_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":311,"last_update":"2024-06-03T20:38:33.692151Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000322/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000322/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-12-01T15:29:48.229274","modified":"2022-09-26T09:05:27.737158","version":"v-2.0.2"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_site_annotation_uniprotkb.csv","filename":"human_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Site Annotation (UniProtKB) dataset contains human [taxid:9606] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"60df3ef1ac54ee01dfe0d6b74aca456b6c87555687e6081a2398ed7673f7b769","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_site_annotation_uniprotkb.csv","filename":"human_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_site_annotation_uniprotkb.stat.csv","filename":"human_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.720000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000322/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000322/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-12-01T15:29:48.229274","modified":"2022-09-26T09:05:27.737158","version":"v-2.1.1"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_site_annotation_uniprotkb.csv","filename":"human_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Site Annotation (UniProtKB) dataset contains human [taxid:9606] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"1de5089bdb6eeacb92529d45161e8da8","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_site_annotation_uniprotkb.csv","filename":"human_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_site_annotation_uniprotkb.stat.csv","filename":"human_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:20.376000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000323/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000323/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-12-01T15:54:04.720467","modified":"2024-06-03T20:39:14.366Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Enzyme Annotation (UniProtKB) dataset contains Homo sapiens [taxid:9606] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"8b7b367bc7507efa501c2f1e6d1bffbfd25299fab8368d564c986bbfe455925c","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_enzyme_annotation_uniprotkb.csv","filename":"human_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"human_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":317,"last_update":"2024-06-03T20:39:14.366848Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000323/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000323/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-12-01T15:54:04.720467","modified":"2022-09-26T09:05:27.769723","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_enzyme_annotation_uniprotkb.csv","filename":"human_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Enzyme Annotation (UniProtKB) dataset contains human [taxid:9606] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions.  The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"f747e2743563a891e0255ae3d55cfe0a388f2e78e83ac5b9a66f90b6d9c1451e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_enzyme_annotation_uniprotkb.csv","filename":"human_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"human_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.955000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000323/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000323/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-12-01T15:54:04.720467","modified":"2022-09-26T09:05:27.769723","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_enzyme_annotation_uniprotkb.csv","filename":"human_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Protein Enzyme Annotation (UniProtKB) dataset contains human [taxid:9606] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions.  The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"c14ae35d61aab129466d619c105e669e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_enzyme_annotation_uniprotkb.csv","filename":"human_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"human_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:20.574000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000324/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000324/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-12-01T15:59:48.968222","modified":"2024-06-03T20:39:33.958Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Enzyme Annotation (UniProtKB) dataset contains Mus musculus [taxid:10090] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"0b2190a7cd3c64e71df487542a2ad32594fa026c2184319c383b1513b33bc748","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_enzyme_annotation_uniprotkb.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":318,"last_update":"2024-06-03T20:39:33.958973Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000324/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000324/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-12-01T15:59:48.968222","modified":"2022-09-26T09:05:27.699987","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_enzyme_annotation_uniprotkb.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Enzyme Annotation (UniProtKB) dataset contains mouse [taxid:10090] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"ac086d505a528f2f9184080606ce69c0ad90ce21cbe8183b7f3a440b5623bd4f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_enzyme_annotation_uniprotkb.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.091000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000324/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000324/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-12-01T15:59:48.968222","modified":"2022-09-26T09:05:27.699987","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_enzyme_annotation_uniprotkb.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Enzyme Annotation (UniProtKB) dataset contains mouse [taxid:10090] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"5c8c9df38f9157c7622941cb23a3affa","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_enzyme_annotation_uniprotkb.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:20.768000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000325/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000325/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-12-01T16:01:52.242488","modified":"2024-06-03T20:39:58.246Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Enzyme Annotation (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"879b5af01584e9b80e49162004fac399ef56341b080117564c831d3f7cccfdc4","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_enzyme_annotation_uniprotkb.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":321,"last_update":"2024-06-03T20:39:58.246708Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000325/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000325/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-12-01T16:01:52.242488","modified":"2022-09-26T09:05:27.710226","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_enzyme_annotation_uniprotkb.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Enzyme Annotation (UniProtKB) dataset contains rat [taxid:10116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"a978c3ac704011ac2493d831a4e3fb64ce28c8e2a4cc9d5208da6463effe9945","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_enzyme_annotation_uniprotkb.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.818000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000325/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000325/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-12-01T16:01:52.242488","modified":"2022-09-26T09:05:27.710226","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_enzyme_annotation_uniprotkb.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Enzyme Annotation (UniProtKB) dataset contains rat [taxid:10116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"7c24809a85c967697b8c2bc9fee75b42","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_enzyme_annotation_uniprotkb.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:20.961000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000326/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000326/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"feed7b371a00a4aefd2d1e2f3475ed7dc3148a29c1a07313ea500ad736ef04fc","provenance_domain":{"name":"Fully determined glycans","version":"v-0.0.0","created":"2019-12-02T15:34:41.971945","modified":"2024-05-17T11:23:56.334Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides a set of glycans which are fully determined. Each glycan is associated with a GlyTouCan Accession. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Fully determined"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script was used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_fully_determined.csv","filename":"glycan_fully_determined.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_fully_determined.stat.csv","filename":"glycan_fully_determined.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":243,"last_update":"2024-05-17T11:23:56.334262Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000326/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000326/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Fully determined glycans","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-12-02T15:34:41.971945","modified":"2022-09-26T09:05:27.644024","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Fully determined"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/fully_determined.csv","filename":"fully_determined.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_fully_determined.csv","filename":"glycan_fully_determined.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script was used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides a set of glycans which are fully determined. Each glycan is associated with a GlyTouCan Accession. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"etag":"695e2c258ef1ad001b090d6f2c6c35d6c6cf52a5672b83e267794cfa53866162","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"subsumption.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_fully_determined.csv","filename":"glycan_fully_determined.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_fully_determined.stat.csv","filename":"glycan_fully_determined.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.988000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000326/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000326/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5fad328be870224c7cd70979abcd26eb","provenance_domain":{"name":"Fully determined glycans","version":"v-2.1.1","created":"2019-12-02T15:34:41.971945","modified":"2023-03-31T18:49:15.929Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides a set of glycans which are fully determined. Each glycan is associated with a GlyTouCan Accession. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Fully determined"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/fully_determined.csv","filename":"fully_determined.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_fully_determined.csv","filename":"glycan_fully_determined.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script was used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"subsumption.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_fully_determined.csv","filename":"glycan_fully_determined.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_fully_determined.stat.csv","filename":"glycan_fully_determined.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:21.145000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000327/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000327/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-12-04T12:16:57.929402","modified":"2024-06-03T20:40:19.192Z","version":"v-0.0.0"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts it as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Site Annotation (UniProtKB) dataset contains Mus musculus [taxid:10090] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"d9b88df0a360bb2932e74e885af948a0698f8d62070a65c0adece4309a8c8863","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_site_annotation_uniprotkb.csv","filename":"mouse_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_site_annotation_uniprotkb.stat.csv","filename":"mouse_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":312,"last_update":"2024-06-03T20:40:19.192305Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000327/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000327/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-12-04T12:16:57.929402","modified":"2022-09-26T09:05:27.658064","version":"v-2.0.2"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_site_annotation_uniprotkb.csv","filename":"mouse_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts it as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Site Annotation (UniProtKB) dataset contains mouse [taxid:10090] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"175a4e546bb82a5ac3a853fc894eaf66e2cfd34200616f062640ebbf5b1168ef","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_site_annotation_uniprotkb.csv","filename":"mouse_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_site_annotation_uniprotkb.stat.csv","filename":"mouse_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.259000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000327/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000327/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-12-04T12:16:57.929402","modified":"2022-09-26T09:05:27.658064","version":"v-2.1.1"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_site_annotation_uniprotkb.csv","filename":"mouse_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts it as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Site Annotation (UniProtKB) dataset contains mouse [taxid:10090] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"f3d49e4fd3965c29b24cd1a1eeb88efa","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_site_annotation_uniprotkb.csv","filename":"mouse_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_site_annotation_uniprotkb.stat.csv","filename":"mouse_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:21.330000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000328/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000328/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2019-12-04T12:24:09.578947","modified":"2024-06-03T20:40:39.587Z","version":"v-0.0.0"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Site Annotation (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"4ae8e03d9da75aeb874abfd6ea7d13da28cf2ae3295eea987fc0873b199c4a67","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_site_annotation_uniprotkb.csv","filename":"rat_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_site_annotation_uniprotkb.stat.csv","filename":"rat_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":315,"last_update":"2024-06-03T20:40:39.587219Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000328/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000328/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2019-12-04T12:24:09.578947","modified":"2022-09-26T09:05:27.686743","version":"v-2.0.2"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_site_annotation_uniprotkb.csv","filename":"rat_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Site Annotation (UniProtKB) dataset contains rat [taxid:10116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"3121d3daa1b2f97ed60852f64e18fd3a058a471ed053a568b5ea2dff16b01293","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_site_annotation_uniprotkb.csv","filename":"rat_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_site_annotation_uniprotkb.stat.csv","filename":"rat_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.543000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000328/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000328/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2019-12-04T12:24:09.578947","modified":"2022-09-26T09:05:27.686743","version":"v-2.1.1"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_site_annotation_uniprotkb.csv","filename":"rat_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Site Annotation (UniProtKB) dataset contains rat [taxid:10116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"52f7f6c70ce827ad33ff21cc5c12c7d0","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_site_annotation_uniprotkb.csv","filename":"rat_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_site_annotation_uniprotkb.stat.csv","filename":"rat_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:21.519000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000329/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000329/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (GlyConnect) ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-02-10T10:16:50.152756","modified":"2024-05-17T11:23:56.452Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (human_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosylation Sites (GlyConnect) dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Homo sapiens). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"5cd6948913d70d838c71d658917bf3e043ea88da98235ff894dd66b9ef078f42","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":521,"last_update":"2024-05-17T11:23:56.452247Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000329/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000329/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (GlyConnect) ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T10:16:50.152756","modified":"2022-09-26T09:05:27.721392","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glyconnect_human_2020_06_08_10_37_47.json","filename":"glyconnect_human_2020_06_08_10_37_47.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/human_proteoform_glycosylation_sites_glyconnect.1.log","filename":"human_proteoform_glycosylation_sites_glyconnect.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (human_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosylation Sites (GlyConnect) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Homo sapiens). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"b0a997b3a46c1be195a4ce7485bdb63e9c0db26d40a463dec5f25c582c3732fe","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"glyconnect_human.json","uri":"https:/data.glygen.org/ln2downloads/glyconnect/2022_03_14/glyconnect_human.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.926000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000329/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000329/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (GlyConnect) ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-02-10T10:16:50.152756","modified":"2022-09-26T09:05:27.721392","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glyconnect_human_2020_06_08_10_37_47.json","filename":"glyconnect_human_2020_06_08_10_37_47.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/human_proteoform_glycosylation_sites_glyconnect.1.log","filename":"human_proteoform_glycosylation_sites_glyconnect.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (human_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Glycosylation Sites (GlyConnect) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Homo sapiens). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"76b6611fddcce68fe9ce79b99df1f180","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"glycosylations?taxonomy=Homo sapiens","uri":"/data/shared/glyds/downloads/glyconnect/2023_05_18/glycosylations?taxonomy=Homo sapiens"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:21.702000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000330/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000330/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8a09e4f97d0e7a33d06dfe968a381685606ba829b7f964f65d2855ad20d332ce","provenance_domain":{"name":"Mouse Glycosylation Sites (GlyConnect) ","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-02-10T12:16:18.548585","modified":"2024-12-10T17:41:14.312Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Sites (GlyConnect) dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Mus musculus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycosylation based on amino acid (i.e., if a N-linked is associated with Ser/Thr residue, etc.,). 4) If the glyco-site is not reported and the glycosylation type is ambiguous (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan master list. All the flagged entries are added in the log file (mouse_proteoform_glycosylation_sites_glyconnect.1.log)"}],"keywords":["glycosylation","reported glycosylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":631,"last_update":"2024-12-10T17:41:14.312548Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000330/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000330/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (GlyConnect) ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T12:16:18.548585","modified":"2022-09-26T09:05:27.645592","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glyconnect_mouse_2020_06_08_10_41_58.json","filename":"glyconnect_mouse_2020_06_08_10_41_58.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycosylation based on amino acid (i.e., if a N-linked is associated with Ser/Thr residue, etc.,). 4) If the glyco-site is not reported and the glycosylation type is ambiguous (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan master list. All the flagged entries are added in the log file (mouse_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (GlyConnect) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Mus musculus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"c1fe3c1cfd9da4028d211941d0365527825666015c9d7585c7120554b4058152","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"glyconnect_mouse.json","uri":"https:/data.glygen.org/ln2downloads/glyconnect/2022_03_14/glyconnect_mouse.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:15Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000330/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000330/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (GlyConnect) ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-02-10T12:16:18.548585","modified":"2022-09-26T09:05:27.645592","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glyconnect_mouse_2020_06_08_10_41_58.json","filename":"glyconnect_mouse_2020_06_08_10_41_58.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycosylation based on amino acid (i.e., if a N-linked is associated with Ser/Thr residue, etc.,). 4) If the glyco-site is not reported and the glycosylation type is ambiguous (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan master list. All the flagged entries are added in the log file (mouse_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (GlyConnect) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Mus musculus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"21d4e10d5cc1504667e3c0a601f865d0","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"glycosylations?taxonomy=Mus musculus","uri":"/data/shared/glyds/downloads/glyconnect/2023_05_18/glycosylations?taxonomy=Mus musculus"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:21.896000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000331/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000331/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e34086b1257c84e055d179d4360f094b62950145a35d463e991389c1b434e305","provenance_domain":{"name":"Rat Glycosylation Sites (GlyConnect) ","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-02-10T12:21:08.095461","modified":"2024-12-10T18:53:58.069Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycosylation Sites (GlyConnect) dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Rattus Norvegicus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycosylation based on amino acid (i.e., if a N-linked is associated with Ser/Thr residue, etc.,). 4) If the glyco-site is not reported and the glycosylation type is ambiguous (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan master list. All the flagged entries are added in the log file (rat_proteoform_glycosylation_sites_glyconnect.1.log)"}],"keywords":["glycosylation","reported glycosylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":641,"last_update":"2024-12-10T18:53:58.069932Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000331/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000331/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (GlyConnect) ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T12:21:08.095461","modified":"2022-09-26T09:05:27.655566","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glyconnect_rat_2020_06_08_1043_10.json","filename":"glyconnect_rat_2020_06_08_1043_10.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/rat_proteoform_glycosylation_sites_glyconnect.1.log","filename":"rat_proteoform_glycosylation_sites_glyconnect.1.log"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycosylation based on amino acid (i.e., if a N-linked is associated with Ser/Thr residue, etc.,). 4) If the glyco-site is not reported and the glycosylation type is ambiguous (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan master list. All the flagged entries are added in the log file (rat_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Glycosylation Sites (GlyConnect) dataset contains rat [taxid:10116] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Rattus Norvegicus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"0aeb1ed66c1ce4aa8076fb4da90523aeaf7daeefa886a37b24898fe2e267a96e","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"glyconnect_rat.json","uri":"https:/data.glygen.org/ln2downloads/glyconnect/2022_03_14/glyconnect_rat.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.949000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000331/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000331/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (GlyConnect) ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-02-10T12:21:08.095461","modified":"2022-09-26T09:05:27.655566","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glyconnect_rat_2020_06_08_1043_10.json","filename":"glyconnect_rat_2020_06_08_1043_10.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/rat_proteoform_glycosylation_sites_glyconnect.1.log","filename":"rat_proteoform_glycosylation_sites_glyconnect.1.log"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycosylation based on amino acid (i.e., if a N-linked is associated with Ser/Thr residue, etc.,). 4) If the glyco-site is not reported and the glycosylation type is ambiguous (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan master list. All the flagged entries are added in the log file (rat_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Glycosylation Sites (GlyConnect) dataset contains rat [taxid:10116] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Rattus Norvegicus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"137948e64032f79f20239eaae1da1892","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"glycosylations?taxonomy=Rattus norvegicus","uri":"/data/shared/glyds/downloads/glyconnect/2023_05_18/glycosylations?taxonomy=Rattus norvegicus"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:22.090000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000332/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000332/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Human Glycan Interaction Data (MatrixDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-02-10T12:42:38.432328","modified":"2024-05-21T16:20:04.361Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Glycan Interaction Data (MatrixDB) dataset contains interaction data between Homo sapiens[taxid:9606] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"a9d6d04b37cd4fd33bed3424134ce44be88ebe22265f1129ef2ed83f9e35b26c","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_matrixdb.csv","filename":"human_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_matrixdb.stat.csv","filename":"human_protein_matrixdb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":304,"last_update":"2024-05-21T16:20:04.361056Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000332/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000332/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Interaction data (MatrixDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T12:42:38.432328","modified":"2022-09-26T09:05:27.698172","version":"v-2.0.2"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_matrixdb.csv","filename":"human_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Interaction data (MatrixDB) dataset contains interaction data between Human [taxid:9606] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"d232c4ef61a3265669b7d9dd4223c3aae7ae3b206d2e7daa65d4f438deab4147","io_domain":{"input_subdomain":[{"uri":{"filename":"matrix_db_label.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/matrix_db_label.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/matrixdb.tsv"}},{"uri":{"filename":"matrixdb_CORE.csv","uri":"https:/data.glygen.org/ln2downloads/matrixdb/2019_08_07/matrixdb_CORE.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_matrixdb.csv","filename":"human_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_matrixdb.stat.csv","filename":"human_protein_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.998000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000332/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000332/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Interaction data (MatrixDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-02-10T12:42:38.432328","modified":"2022-09-26T09:05:27.698172","version":"v-2.1.1"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_matrixdb.csv","filename":"human_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Human Interaction data (MatrixDB) dataset contains interaction data between Human [taxid:9606] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"be562a2c006349c3e76710098253b8c6","io_domain":{"input_subdomain":[{"uri":{"filename":"matrix_db_label.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/matrix_db_label.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/matrixdb.tsv"}},{"uri":{"filename":"matrixdb_CORE.tab","uri":"/data/shared/glyds/downloads/matrixdb/2023_05_22/matrixdb_CORE.tab"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_matrixdb.csv","filename":"human_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_matrixdb.stat.csv","filename":"human_protein_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:22.285000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000333/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000333/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Mouse Glycan Interaction Data (MatrixDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-02-10T14:02:01.224476","modified":"2024-05-21T16:19:31.828Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLY_000007)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Glycan Interaction Data (MatrixDB) dataset contains interaction data between Mus musculus [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"cab4b3e276e8a8f0e52e6782b1656a670c0288733505b34850122ef8f9295f25","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_matrixdb.csv","filename":"mouse_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_matrixdb.stat.csv","filename":"mouse_protein_matrixdb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":306,"last_update":"2024-05-21T16:19:31.828343Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000333/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000333/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Interaction data (MatrixDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T14:02:01.224476","modified":"2022-09-26T09:05:27.711895","version":"v-2.0.2"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_matrixdb.csv","filename":"mouse_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Interaction data (MatrixDB) dataset contains interaction data between Mouse [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"407444d48898ef43ad2d4541fa19c28a35e752cac25fed6d84c7d61cde9174e0","io_domain":{"input_subdomain":[{"uri":{"filename":"matrix_db_label.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/matrix_db_label.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/matrixdb.tsv"}},{"uri":{"filename":"matrixdb_CORE.csv","uri":"https:/data.glygen.org/ln2downloads/matrixdb/2019_08_07/matrixdb_CORE.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_matrixdb.csv","filename":"mouse_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_matrixdb.stat.csv","filename":"mouse_protein_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.340000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000333/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000333/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Interaction data (MatrixDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-02-10T14:02:01.224476","modified":"2022-09-26T09:05:27.711895","version":"v-2.1.1"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_matrixdb.csv","filename":"mouse_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Interaction data (MatrixDB) dataset contains interaction data between Mouse [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"5b25d9e8822280f6b12267bb2e4b8061","io_domain":{"input_subdomain":[{"uri":{"filename":"matrix_db_label.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/matrix_db_label.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/matrixdb.tsv"}},{"uri":{"filename":"matrixdb_CORE.tab","uri":"/data/shared/glyds/downloads/matrixdb/2023_05_22/matrixdb_CORE.tab"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_matrixdb.csv","filename":"mouse_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_matrixdb.stat.csv","filename":"mouse_protein_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:22.481000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000334/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000334/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Interaction data (MatrixDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-02-10T14:05:00.767732","modified":"2024-05-17T11:23:56.650Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Interaction data (MatrixDB) dataset contains interaction data between Rat [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"7d195da5c55d6d5ce6c7aedf6ee41810aace35ff5bc0ba60503ec2bca3137ac6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_matrixdb.stat.csv","filename":"rat_protein_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":288,"last_update":"2024-05-17T11:23:56.650346Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000334/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000334/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Interaction data (MatrixDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T14:05:00.767732","modified":"2022-09-26T09:05:27.735775","version":"v-2.0.2"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Interaction data (MatrixDB) dataset contains interaction data between Rat [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"08a1499fd2667cd3bad50dd56b4b3de40c739c472630beabc10760abe574a68c","io_domain":{"input_subdomain":[{"uri":{"filename":"matrix_db_label.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/matrix_db_label.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/matrixdb.tsv"}},{"uri":{"filename":"matrixdb_CORE.csv","uri":"https:/data.glygen.org/ln2downloads/matrixdb/2019_08_07/matrixdb_CORE.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_matrixdb.stat.csv","filename":"rat_protein_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.939000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000334/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000334/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Interaction data (MatrixDB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-02-10T14:05:00.767732","modified":"2022-09-26T09:05:27.735775","version":"v-2.1.1"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Interaction data (MatrixDB) dataset contains interaction data between Rat [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"etag":"c1c1e40520402468ca12c17d23d5e07a","io_domain":{"input_subdomain":[{"uri":{"filename":"matrix_db_label.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/matrix_db_label.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/matrixdb.tsv"}},{"uri":{"filename":"matrixdb_CORE.tab","uri":"/data/shared/glyds/downloads/matrixdb/2023_05_22/matrixdb_CORE.tab"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_matrixdb.stat.csv","filename":"rat_protein_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:22.663000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000335/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000335/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"88cff086a9b8b51df20dd807c55edac76122805a829a6d9a5bb1b5d838620eed","provenance_domain":{"name":"HCV1a Glycosylation Sites (Literature + UniCarbKB)","version":"v-0.0.0","created":"2020-02-10T14:13:38.047090","modified":"2024-05-17T11:23:56.687Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The HCV1a Glycosylation Sites (Literature + UniCarbKB) dataset contains glycosylation sites experimentally reported on Hepatitis C virus (isolate H77) [taxid:63746] protein. The data was extracted from publication PMID:18187336. (Iacob RE, Perdivara I, Przybylski M, Tomer KB. Mass spectrometric characterization of glycosylation of hepatitis C virus E2 envelope glycoprotein reveals extended microheterogeneity of N-glycans. J Am Soc Mass Spectrom. 2008;19(3):428–444. doi:10.1016/j.jasms.2007.11.022). The glycan compositions from the publication were assigned GlyTouCan accessions by UniCarbKB. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"description_domain":{"keywords":["reported glycosylation","HCV"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"1) The data was extracted from the publications using supplemental material (Table 1,2,3). 2) The GenBank accession number (AF009606) retrieved from the paper was matched to the best hit UniProtKB Ac. (P27958) using the NCBI BLAST. 3) The glycan compositions provided by the paper were mapped to GlyTouCan Accession manually.  4) The source cell-line and mass-spectrometry data such as analyzer, chromatography, etc. were also extracted from the paper. 5) QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions and checked the validity of amino acid and glycosite position on the .fasta sequence in UniProtKB for that protein."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":692,"last_update":"2024-05-17T11:23:56.687328Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000335/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000335/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"external","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Glycosylation Sites (Literature + UniCarbKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T14:13:38.047090","modified":"2022-09-26T09:05:27.771333","version":"v-2.0.2"},"description_domain":{"keywords":["reported glycosylation","HCV"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"1) The data was extracted from the publications using supplemental material (Table 1,2,3). 2) The GenBank accession number (AF009606) retrieved from the paper was matched to the best hit UniProtKB Ac. (P27958) using the NCBI BLAST. 3) The glycan compositions provided by the paper were mapped to GlyTouCan Accession manually.  4) The source cell-line and mass-spectrometry data such as analyzer, chromatography, etc. were also extracted from the paper. 5) QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions and checked the validity of amino acid and glycosite position on the .fasta sequence of the 2019-09 UniProtKB release for that protein."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The HCV1a [TaxID:1108] glycosylations sites dataset contains glycosylation sites experimentally reported on Hepatitis C Virus 1a protein. The data was extracted from publication PMID:18187336. (Iacob RE, Perdivara I, Przybylski M, Tomer KB. Mass spectrometric characterization of glycosylation of hepatitis C virus E2 envelope glycoprotein reveals extended microheterogeneity of N-glycans. J Am Soc Mass Spectrom. 2008;19(3):428–444. doi:10.1016/j.jasms.2007.11.022). The glycan compositions from publication [PMID:18187336] were assigned to GlyTouCan accessions by UniCarbKB. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"etag":"017975f2ff55c4d30b3d881b0919867fd77092b0b3bb2c13491db389be1cca6e","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_sites_lit_23090970_s2.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_23090970_s2.csv"}},{"uri":{"filename":"glycosylation_sites_lit_23090970_s5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_23090970_s5.csv"}},{"uri":{"filename":"glycosylation_sites_lit_24190977_s5.cs","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_24190977_s5.cs"}},{"uri":{"filename":"glycosylation_sites_lit_x_sx.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_x_sx.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.238000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000335/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000335/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e7891462bf176093e6f6abf742bc7e40","provenance_domain":{"name":"HCV1a Glycosylation Sites (Literature + UniCarbKB)","version":"v-2.1.1","created":"2020-02-10T14:13:38.047090","modified":"2023-03-31T18:51:45.962Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The HCV1a [TaxID:1108] glycosylations sites dataset contains glycosylation sites experimentally reported on Hepatitis C Virus 1a protein. The data was extracted from publication PMID:18187336. (Iacob RE, Perdivara I, Przybylski M, Tomer KB. Mass spectrometric characterization of glycosylation of hepatitis C virus E2 envelope glycoprotein reveals extended microheterogeneity of N-glycans. J Am Soc Mass Spectrom. 2008;19(3):428–444. doi:10.1016/j.jasms.2007.11.022). The glycan compositions from publication [PMID:18187336] were assigned to GlyTouCan accessions by UniCarbKB. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"description_domain":{"keywords":["reported glycosylation","HCV"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"1) The data was extracted from the publications using supplemental material (Table 1,2,3). 2) The GenBank accession number (AF009606) retrieved from the paper was matched to the best hit UniProtKB Ac. (P27958) using the NCBI BLAST. 3) The glycan compositions provided by the paper were mapped to GlyTouCan Accession manually.  4) The source cell-line and mass-spectrometry data such as analyzer, chromatography, etc. were also extracted from the paper. 5) QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions and checked the validity of amino acid and glycosite position on the .fasta sequence of the 2019-09 UniProtKB release for that protein."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_sites_lit_23090970_s2.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_23090970_s2.csv"}},{"uri":{"filename":"glycosylation_sites_lit_23090970_s5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_23090970_s5.csv"}},{"uri":{"filename":"glycosylation_sites_lit_24190977_s5.cs","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_24190977_s5.cs"}},{"uri":{"filename":"glycosylation_sites_lit_x_sx.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_x_sx.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:22.846000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000336/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000336/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlycoProtDB cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Xref GlycoProtDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyTouCan ","contribution":["authoredBy"],"name":"Kiyoko F. Aoki-Kinoshita","email":"kkiyoko@soka.ac.jp"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-02-10T14:47:12.024589","modified":"2024-05-17T11:23:56.725Z","version":"v-0.0.0"},"description_domain":{"keywords":["GlycoProtDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was received directly from the author (Kiyoko F. Aoki-Kinoshita). all the accessions from the input file were checked in the UniProtKB through ID mapping tool. It was found that all the UniProtKB accessions belonged to the Mouse [TaxID:10090] species. The QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions. Any GlycoProtDB ID which was mapped to a protein outside GlyGen protein master list was excluded from the output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse (TaxID:10090) Xref GlycoProtDB  contains x-refs to IDs present in the GlycoProtDB database (https://acgg.asia/gpdb2/index). If you use this dataset please provide proper attribution to GlycoProtDB and GlyGen. "],"etag":"b23ddd38487ab0a37874ee3c7f223e64ad0f2066b4aed231fc9b286c30c9bff4","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_glycoprotdb.csv","filename":"mouse_protein_xref_glycoprotdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_glycoprotdb.stat.csv","filename":"mouse_protein_xref_glycoprotdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":219,"last_update":"2024-05-17T11:23:56.725870Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000336/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000336/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlycoProtDB cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Xref GlycoProtDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyTouCan ","contribution":["authoredBy"],"name":"Kiyoko F. Aoki-Kinoshita","email":"kkiyoko@soka.ac.jp"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-02-10T14:47:12.024589","modified":"2022-09-26T09:05:27.604244","version":"v-2.0.2"},"description_domain":{"keywords":["GlycoProtDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/protein_xref_glycoprotdb.csv","filename":"protein_xref_glycoprotdb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_glycoprotdb.csv","filename":"mouse_protein_xref_glycoprotdb.csv"}],"prerequisite":[],"description":"The input file was received directly from the author (Kiyoko F. Aoki-Kinoshita). all the accessions from the input file were checked in the UniProtKB through ID mapping tool. It was found that all the UniProtKB accessions belonged to the Mouse [TaxID:10090] species. The QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions. Any GlycoProtDB ID which was mapped to a protein outside GlyGen protein master list was excluded from the output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse (TaxID:10090) Xref GlycoProtDB  contains x-refs to IDs present in the GlycoProtDB database (https://acgg.asia/gpdb2/index). If you use this dataset please provide proper attribution to GlycoProtDB and GlyGen. "],"etag":"933ef976df6af9217f2104c859f5938eba312012967f6c80271d528b1ab73cbc","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_xref_glycoprotdb.csv","uri":"https:/data.glygen.org/ln2downloads/glycoprotdb/protein_xref_glycoprotdb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_glycoprotdb.csv","filename":"mouse_protein_xref_glycoprotdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_glycoprotdb.stat.csv","filename":"mouse_protein_xref_glycoprotdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.007000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000336/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000336/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlycoProtDB cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Xref GlycoProtDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyTouCan ","contribution":["authoredBy"],"name":"Kiyoko F. Aoki-Kinoshita","email":"kkiyoko@soka.ac.jp"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-02-10T14:47:12.024589","modified":"2022-09-26T09:05:27.604244","version":"v-2.1.1"},"description_domain":{"keywords":["GlycoProtDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/protein_xref_glycoprotdb.csv","filename":"protein_xref_glycoprotdb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_glycoprotdb.csv","filename":"mouse_protein_xref_glycoprotdb.csv"}],"prerequisite":[],"description":"The input file was received directly from the author (Kiyoko F. Aoki-Kinoshita). all the accessions from the input file were checked in the UniProtKB through ID mapping tool. It was found that all the UniProtKB accessions belonged to the Mouse [TaxID:10090] species. The QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions. Any GlycoProtDB ID which was mapped to a protein outside GlyGen protein master list was excluded from the output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse (TaxID:10090) Xref GlycoProtDB  contains x-refs to IDs present in the GlycoProtDB database (https://acgg.asia/gpdb2/index). If you use this dataset please provide proper attribution to GlycoProtDB and GlyGen. "],"etag":"62d47008a74a14ed12df8f8ae78533fa","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_xref_glycoprotdb.csv","uri":"/data/shared/glyds/downloads/glycoprotdb/protein_xref_glycoprotdb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_glycoprotdb.csv","filename":"mouse_protein_xref_glycoprotdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_glycoprotdb.stat.csv","filename":"mouse_protein_xref_glycoprotdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:23.039000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000337/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000337/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoEpitope cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycoEpitope","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-02T12:24:13.829417","modified":"2024-05-17T11:23:56.764Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoEpitope","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlycoEpitope for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.glycoepitope.jp/"],"etag":"058882a45494a5f27a19bb74d04b7a4e776b310d43f48d5a54f94c9b64e55b9e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glycoepitope.csv","filename":"glycan_xref_glycoepitope.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glycoepitope.stat.csv","filename":"glycan_xref_glycoepitope.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":296,"last_update":"2024-05-17T11:23:56.764347Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000337/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000337/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoEpitope cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycoEpitope","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-02T12:24:13.829417","modified":"2022-09-26T09:05:27.630675","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoEpitope","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycoepitope.tsv","filename":"glycoepitope.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_glycoepitope.csv","filename":"glycan_xref_glycoepitope.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlycoEpitope for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.glycoepitope.jp/"],"etag":"937f3fcdf513de5af758d38999943aff566a15b2e5b79cdd78ba99fddb2a0fa4","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycoepitope.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/glycoepitope.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glycoepitope.csv","filename":"glycan_xref_glycoepitope.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glycoepitope.stat.csv","filename":"glycan_xref_glycoepitope.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.681000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000337/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000337/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoEpitope cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycoEpitope","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-02T12:24:13.829417","modified":"2022-09-26T09:05:27.630675","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoEpitope","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycoepitope.tsv","filename":"glycoepitope.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_glycoepitope.csv","filename":"glycan_xref_glycoepitope.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlycoEpitope for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.glycoepitope.jp/"],"etag":"45214fa78c14e2f8c200b8cbf50ced2c","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycoepitope.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/glycoepitope.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glycoepitope.csv","filename":"glycan_xref_glycoepitope.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glycoepitope.stat.csv","filename":"glycan_xref_glycoepitope.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:23.223000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000338/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000338/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"MatrixDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref MatrixDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-02T12:32:42.836682","modified":"2024-05-17T11:23:56.802Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","MatrixDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to MatrixDB for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://matrixdb.univ-lyon1.fr/"],"etag":"b28d15e4fe7d0be7a20dff9ded5ff39a4bc15421b34502f34c0ceb50e7642b69","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_matrixdb.csv","filename":"glycan_xref_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_matrixdb.stat.csv","filename":"glycan_xref_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":293,"last_update":"2024-05-17T11:23:56.802107Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000338/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000338/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"MatrixDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref MatrixDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-02T12:32:42.836682","modified":"2022-09-26T09:05:27.748434","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","MatrixDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/matrixdb.tsv","filename":"matrixdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_matrixdb.csv","filename":"glycan_xref_matrixdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to MatrixDB for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://matrixdb.univ-lyon1.fr/"],"etag":"b220c63df29104b6ee466708d8393c7580c4d3161be237fa0ef913195929104c","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/matrixdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_matrixdb.csv","filename":"glycan_xref_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_matrixdb.stat.csv","filename":"glycan_xref_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.085000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000338/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000338/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"MatrixDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref MatrixDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-02T12:32:42.836682","modified":"2022-09-26T09:05:27.748434","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","MatrixDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/matrixdb.tsv","filename":"matrixdb.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_matrixdb.csv","filename":"glycan_xref_matrixdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to MatrixDB for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://matrixdb.univ-lyon1.fr/"],"etag":"55ad4b34ac459897c26227fd83a89df2","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"matrixdb.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/matrixdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_matrixdb.csv","filename":"glycan_xref_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_matrixdb.stat.csv","filename":"glycan_xref_matrixdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:23.411000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000339/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000339/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (PNG format)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-02T12:39:45.400128","modified":"2024-05-17T11:23:56.839Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","png"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-png.tbz.?? > images-snfg-extended-png.tbz 2. tar xvf images-snfg-extended-png.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"a93ef2fb587e66ca019f0066ad1c07845ab51d962938affc51dec02919226d9b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_images_snfg_extended_png.tar.gz","filename":"glycan_images_snfg_extended_png.tar.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_images_snfg_extended_png.tar.stat.csv","filename":"glycan_images_snfg_extended_png.tar.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":245,"last_update":"2024-05-17T11:23:56.839044Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000339/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000339/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (PNG format)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-02T12:39:45.400128","modified":"2022-09-26T09:05:27.757124","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","png"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/images-snfg-extended-png.tbz.00","filename":"images-snfg-extended-png.tbz.00"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/images-snfg-extended-png.tbz.01","filename":"images-snfg-extended-png.tbz.01"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_images_snfg_extended_png.tar.gz","filename":"glycan_images_snfg_extended_png.tar.gz"}],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-png.tbz.?? > images-snfg-extended-png.tbz 2. tar xvf images-snfg-extended-png.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"d378d7dae19f32e99d1431aa36f236a57a4fb485e18899f88610fafa0e951a6b","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_images_snfg_extended_png.tar.gz","filename":"glycan_images_snfg_extended_png.tar.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_images_snfg_extended_png.tar.stat.csv","filename":"glycan_images_snfg_extended_png.tar.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.742000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000339/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000339/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (PNG format)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-02T12:39:45.400128","modified":"2022-09-26T09:05:27.757124","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","png"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/images-snfg-extended-png.tbz.00","filename":"images-snfg-extended-png.tbz.00"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/images-snfg-extended-png.tbz.01","filename":"images-snfg-extended-png.tbz.01"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_images_snfg_extended_png.tar.gz","filename":"glycan_images_snfg_extended_png.tar.gz"}],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-png.tbz.?? > images-snfg-extended-png.tbz 2. tar xvf images-snfg-extended-png.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"adbcd1388a824c0f54b0d0dee8930f67","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_images_snfg_extended_png.tar.gz","filename":"glycan_images_snfg_extended_png.tar.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_images_snfg_extended_png.tar.stat.csv","filename":"glycan_images_snfg_extended_png.tar.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:23.596000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000340/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000340/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"names","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Names","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-02T13:49:57.958726","modified":"2024-05-17T11:23:56.875Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Names","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides names for the associated glycan (GlyTouCan Accession) in different formats. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"ff5966aa81da2689d97cd227c3bdf0754d0c45e2f1a10d6af3ae97345d052d33","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_names.csv","filename":"glycan_names.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_names.stat.csv","filename":"glycan_names.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":260,"last_update":"2024-05-17T11:23:56.875851Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000340/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000340/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"names","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Names","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-02T13:49:57.958726","modified":"2022-09-26T09:05:27.620688","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Names","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/names.tsv","filename":"names.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_names.csv","filename":"glycan_names.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides names for the associated glycan (GlyTouCan Accession) in different formats. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"c3e154c20324b57138a66676ab5b8afade884cb70119afe5c5fac55e89464257","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"names.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/names.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_names.csv","filename":"glycan_names.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_names.stat.csv","filename":"glycan_names.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.694000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000340/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000340/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"names","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Names","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-02T13:49:57.958726","modified":"2022-09-26T09:05:27.620688","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Names","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/names.tsv","filename":"names.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_names.csv","filename":"glycan_names.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides names for the associated glycan (GlyTouCan Accession) in different formats. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"ace92c4adc6c3b03ac19c544fc431ab7","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"names.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/names.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_names.csv","filename":"glycan_names.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_names.stat.csv","filename":"glycan_names.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:23.784000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000341/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000341/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Species ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-02T13:55:30.488616","modified":"2024-05-17T11:23:56.914Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides species annotation for the associated glycan (GlyTouCan Accession) generated from direct TaxID annotation and/or inferred via subsumption. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy."],"etag":"92869f251920e2010eb9d00a79f59fa6932be75cefc311f2b7ab606f70fa820f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_species.csv","filename":"glycan_species.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_species.stat.csv","filename":"glycan_species.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2024-05-17T11:23:56.914246Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000341/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000341/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Species ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-02T13:55:30.488616","modified":"2022-09-26T09:05:27.613063","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/species.tsv","filename":"species.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_species.csv","filename":"glycan_species.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides species annotation for the associated glycan (GlyTouCan Accession) generated from direct TaxID annotation and/or inferred via subsumption. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy."],"etag":"0cb075aceb66cbedd90c048f2a5b0057b91532c3daf5e461e6a74b5ffff829f7","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"species_expanded.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/species_expanded.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_species.csv","filename":"glycan_species.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_species.stat.csv","filename":"glycan_species.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.218000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000341/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000341/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Species ","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-02T13:55:30.488616","modified":"2022-09-26T09:05:27.613063","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/species.tsv","filename":"species.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_species.csv","filename":"glycan_species.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides species annotation for the associated glycan (GlyTouCan Accession) generated from direct TaxID annotation and/or inferred via subsumption. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy."],"etag":"add28115ebe985ae17bdf89098f2fc1f","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"species_expanded.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/species_expanded.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_species.csv","filename":"glycan_species.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_species.stat.csv","filename":"glycan_species.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:23.976000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000342/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000342/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e68f73e5669856fef8fa029bece1c57eb8c62b3814e6ece1140f8b978c92d0d0","provenance_domain":{"name":"Glycans with NeuAc (Customized table)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-03-02T14:23:10.848312","modified":"2024-08-02T15:46:32.188Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides glycans that have at least one \"NeuAc\" residue in the current GlyGen dataset (https://data.glygen.org/GLY_000281). The GlyTouCan accessions included in this list have mammalian species annotation (human/mouse/rat) through direct TaxID annotation and/or inferred via subsumption. This table was customized based on a GlyGen user query submitted through GlyGen help on Feb 17th 2020."],"description_domain":{"pipeline_steps":[{"name":"manual","step_number":1,"input_list":[],"description":"Based on the submitted user query (different sialic acid-containing mammalian glycan structures reported in your database), the  list of glycans that have \"NeuAc\" were from input file 1 (monocomp.tsv;column:5 ;filter:not \"0\"). The selected GlyTouCan accessions were mapped to input file 2 (glycan_species.tsv) where the value is \"true\".  "}],"keywords":["Glycan","GlyTouCan Accession","NeuAc","Mammalian species annotation "]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_species_customized_neuac_neugc.csv","filename":"glycan_species_customized_neuac_neugc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_species_customized_neuac_neugc.stat.csv","filename":"glycan_species_customized_neuac_neugc.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/A","filename":"N/A"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NeuAc ","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"Mammalian species annotation","category_name":"tags"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":402,"last_update":"2024-08-02T15:46:32.188043Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000342/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000342/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NeuAc ","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"Mammalian species annotation","category_name":"tags"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycans with NeuAc (Customized table)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-02T14:23:10.848312","modified":"2022-09-26T09:05:27.762294","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NeuAc","Mammalian species annotation "],"pipeline_steps":[{"name":"manual","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/monocomp.tsv","filename":"monocomp.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/species.tsv","filename":"species.tsv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed//data/projects/glygen/generated/v-2.0.2/unreviewed/glycan_species_customized_neuac_neugc.csv","filename":"glycan_species_customized_neuac_neugc.csv"}],"prerequisite":[],"description":"Based on the submitted user query (different sialic acid-containing mammalian glycan structures reported in your database), the  list of glycans that have \"NeuAc\" were from input file 1 (monocomp.tsv;column:5 ;filter:not \"0\"). The selected GlyTouCan accessions were mapped to input file 2 (glycan_species.tsv) where the value is \"true\".  "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/A","filename":"N/A"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides glycans that have at least one \"NeuAc\" residue in the current GlyGen dataset (https://data.glygen.org/GLYDS000281). The GlyTouCan accessions included in this list have mammalian species annotation (human/mouse/rat) through direct TaxID annotation and/or inferred via subsumption. This table was customized based on a GlyGen user query submitted through GlyGen help on Feb 17th 2020."],"etag":"81850650309dcbb48dd756eb760bd3d1a0a3297f7ad2ef30fef494547b864723","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_monosaccharide_composition.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_monosaccharide_composition.csv"}},{"uri":{"filename":"glycan_species.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_species.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_species_customized_neuac_neugc.csv","filename":"glycan_species_customized_neuac_neugc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_species_customized_neuac_neugc.stat.csv","filename":"glycan_species_customized_neuac_neugc.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.420000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000342/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000342/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NeuAc ","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"Mammalian species annotation","category_name":"tags"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycans with NeuAc (Customized table)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-02T14:23:10.848312","modified":"2022-09-26T09:05:27.762294","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NeuAc","Mammalian species annotation "],"pipeline_steps":[{"name":"manual","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/monocomp.tsv","filename":"monocomp.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/species.tsv","filename":"species.tsv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed//data/projects/glygen/generated/v-2.1.1/unreviewed/glycan_species_customized_neuac_neugc.csv","filename":"glycan_species_customized_neuac_neugc.csv"}],"prerequisite":[],"description":"Based on the submitted user query (different sialic acid-containing mammalian glycan structures reported in your database), the  list of glycans that have \"NeuAc\" were from input file 1 (monocomp.tsv;column:5 ;filter:not \"0\"). The selected GlyTouCan accessions were mapped to input file 2 (glycan_species.tsv) where the value is \"true\".  "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/A","filename":"N/A"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides glycans that have at least one \"NeuAc\" residue in the current GlyGen dataset (https://data.glygen.org/GLYDS000281). The GlyTouCan accessions included in this list have mammalian species annotation (human/mouse/rat) through direct TaxID annotation and/or inferred via subsumption. This table was customized based on a GlyGen user query submitted through GlyGen help on Feb 17th 2020."],"etag":"0fca7b29083cdb8a1a99b71e1f01f480","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_monosaccharide_composition.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_monosaccharide_composition.csv"}},{"uri":{"filename":"glycan_species.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_species.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_species_customized_neuac_neugc.csv","filename":"glycan_species_customized_neuac_neugc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_species_customized_neuac_neugc.stat.csv","filename":"glycan_species_customized_neuac_neugc.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:24.165000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000344/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000344/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-12T11:05:17.851540","modified":"2024-05-17T11:23:56.993Z","version":"v-0.0.0"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Proteome Masterlist dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. Please note GlyGen has removed F protein (P0C045 (F_HCV77)) from its masterlist of accessions."],"etag":"0a3b20be33b8c47c19ee4916fbd21d8f9ab0a76e8039527f3fd331a20fe8c556","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_masterlist.stat.csv","filename":"hcv1a_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":407,"last_update":"2024-05-17T11:23:56.993287Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000344/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000344/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-12T11:05:17.851540","modified":"2022-09-26T09:05:27.728036","version":"v-2.0.2"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Proteome Materlist dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020_06 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. Please note GlyGen has removed F protein (P0C045 (F_HCV77)) from its masterlist of accessions."],"etag":"fa38190042483fedeb523a7bc33d88119aa0525e3d83ac04ae52910cf868c9b5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.stat.csv","filename":"hcv1a_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.823000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000344/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000344/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-12T11:05:17.851540","modified":"2022-09-26T09:05:27.728036","version":"v-2.1.1"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Proteome Materlist dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020_06 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. Please note GlyGen has removed F protein (P0C045 (F_HCV77)) from its masterlist of accessions."],"etag":"935df6d6727a76a3a153088eaa4c5075","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.stat.csv","filename":"hcv1a_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:24.352000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000345/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000345/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-12T11:19:29.356135","modified":"2024-06-03T20:31:59.601Z","version":"v-0.0.0"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Proteome Masterlist dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"54e4908ed4a46f568c052dfe82c5f202b44f68499304695a9f9a949a3df03bab","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_masterlist.stat.csv","filename":"hcv1b_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-06-03T20:31:59.601911Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000345/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000345/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-12T11:19:29.356135","modified":"2022-09-26T09:05:27.679671","version":"v-2.0.2"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Proteome Materlist dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"2e3202cd7f38f05d0d0284a7b7acb2d9387dac9a99c5aca724b4bd31d4b041a3","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.stat.csv","filename":"hcv1b_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.728000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000345/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000345/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-12T11:19:29.356135","modified":"2022-09-26T09:05:27.679671","version":"v-2.1.1"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Proteome Materlist dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"732ccc7285c088ef66dfc1b850f5b7cb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.stat.csv","filename":"hcv1b_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:24.540000Z","access_count":48},{"object_id":"https://biocomputeobject.org/GLY_000346/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000346/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-12T11:24:06.518525","modified":"2024-05-17T11:23:57.069Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Canonical (UniProtKB) Sequences dataset contains Hepatitis C virus (isolate H77) [taxid:63746] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"f65dc7aa8a215c388ee3da6393d1d7e19eebc6d26bd65af95e5c6c4ff401ffbf","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_canonicalsequences.stat.csv","filename":"hcv1a_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":267,"last_update":"2024-05-17T11:23:57.069583Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000346/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000346/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-12T11:24:06.518525","modified":"2022-09-26T09:05:27.667836","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Canonical (UniProtKB) Sequences dataset contains hcv1a [taxid:11108] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"db831abc9437d16943c3e380ff2296830ee51b51f6b144b13f671a8b6bcc3b2d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_canonicalsequences.stat.csv","filename":"hcv1a_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.076000Z","access_count":80},{"object_id":"https://biocomputeobject.org/GLY_000346/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000346/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-12T11:24:06.518525","modified":"2022-09-26T09:05:27.667836","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Canonical (UniProtKB) Sequences dataset contains hcv1a [taxid:11108] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"9eafc71cef03aee481ea7d3e5af7929e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_canonicalsequences.stat.csv","filename":"hcv1a_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:24.735000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000347/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000347/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-12T11:33:50.191985","modified":"2024-06-03T20:28:23.192Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Canonical (UniProtKB) Sequences dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"9b2136042ff6fb9d0948880771975bc5c5c3872f119e132bd95cb2ffe52c225a","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_canonicalsequences.stat.csv","filename":"hcv1b_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":316,"last_update":"2024-06-03T20:28:23.192895Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000347/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000347/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-12T11:33:50.191985","modified":"2022-09-26T09:05:27.639526","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Canonical (UniProtKB) Sequences dataset contains hcv1b [taxid:11116] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"b987d7865006241acff3da78fa922d1bcc60d1fb84b3822a5d6a5810ba4ffbd5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_canonicalsequences.stat.csv","filename":"hcv1b_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.331000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000347/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000347/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-12T11:33:50.191985","modified":"2022-09-26T09:05:27.639526","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Canonical (UniProtKB) Sequences dataset contains hcv1b [taxid:11116] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d67c471edd362a58b01a7fcaeaf1b44c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_canonicalsequences.stat.csv","filename":"hcv1b_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:24.924000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000348/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000348/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-12T11:37:55.146916","modified":"2024-05-17T11:23:57.148Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Isoform sequences (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] protein fasta sequences for the hcv1a isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"81ca8b43f805808cf79036799cfb52c880b7a031f64e6c725f7a9207a135e727","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_allsequences.fasta","filename":"hcv1a_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_allsequences.stat.csv","filename":"hcv1a_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":288,"last_update":"2024-05-17T11:23:57.148458Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000348/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000348/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-12T11:37:55.146916","modified":"2022-09-26T09:05:27.716452","version":"v-2.0.2"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_allsequences.fasta","filename":"hcv1a_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Isoform sequences (UniProtKB) dataset contains hcv1a [taxid:11108] protein fasta sequences for the hcv1a isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"62abc5a450c4fc7ebbbbf7f17706e9ff10c71f785ceade0fd35ffc35baf0a0eb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_allsequences.fasta","filename":"hcv1a_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_allsequences.stat.csv","filename":"hcv1a_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.017000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000348/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000348/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-12T11:37:55.146916","modified":"2022-09-26T09:05:27.716452","version":"v-2.1.1"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_allsequences.fasta","filename":"hcv1a_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Isoform sequences (UniProtKB) dataset contains hcv1a [taxid:11108] protein fasta sequences for the hcv1a isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0ededb456c8ddfc9f80683b7d60d4915","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_allsequences.fasta","filename":"hcv1a_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_allsequences.stat.csv","filename":"hcv1a_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:25.107000Z","access_count":32},{"object_id":"https://biocomputeobject.org/GLY_000349/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000349/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-12T11:41:02.468576","modified":"2024-05-17T11:23:57.186Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Isoform sequences (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] protein fasta sequences for the hcv1b isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"ac04a12bb4abb2c044b4e890d5f6a0bbda00e43f03cb2b31d91117a54a0610a0","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_allsequences.fasta","filename":"hcv1b_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_allsequences.stat.csv","filename":"hcv1b_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2024-05-17T11:23:57.186043Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000349/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000349/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-12T11:41:02.468576","modified":"2022-09-26T09:05:27.694593","version":"v-2.0.2"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_allsequences.fasta","filename":"hcv1b_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Isoform sequences (UniProtKB) dataset contains hcv1b [taxid:11116] protein fasta sequences for the hcv1b isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"b691fcf2e4dec2f07d369d2afcd4b44c174a40213f3a2488f8a5e70250c00162","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_allsequences.fasta","filename":"hcv1b_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_allsequences.stat.csv","filename":"hcv1b_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.034000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000349/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000349/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-12T11:41:02.468576","modified":"2022-09-26T09:05:27.694593","version":"v-2.1.1"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_allsequences.fasta","filename":"hcv1b_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Isoform sequences (UniProtKB) dataset contains hcv1b [taxid:11116] protein fasta sequences for the hcv1b isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"c13d966ef2d13ab3aabc3859dc22400d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_allsequences.fasta","filename":"hcv1b_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_allsequences.stat.csv","filename":"hcv1b_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:25.295000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000350/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000350/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T10:14:33.505586","modified":"2024-05-17T11:23:57.225Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence info","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1a accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Sequences Info (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB protein sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"875f3970e7c8aa13f8853a24eec8a19723a3393ceb9cf906b3b4b178324cd21a","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_sequenceinfo.csv","filename":"hcv1a_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_sequenceinfo.stat.csv","filename":"hcv1a_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":287,"last_update":"2024-05-17T11:23:57.225830Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000350/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000350/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T10:14:33.505586","modified":"2022-09-26T09:05:27.666010","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence info","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_sequenceinfo.csv","filename":"hcv1a_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1a accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Sequences Info (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB protein sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0b5e318ccb15712ac07f461bd1ce02a6bfadec51bad47784f27fcc7c24b2ab4f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_sequenceinfo.csv","filename":"hcv1a_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_sequenceinfo.stat.csv","filename":"hcv1a_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.436000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000350/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000350/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T10:14:33.505586","modified":"2022-09-26T09:05:27.666010","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence info","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_sequenceinfo.csv","filename":"hcv1a_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1a accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Sequences Info (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB protein sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e3665fc45f48a1bb5d9c92b6a449c75b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_sequenceinfo.csv","filename":"hcv1a_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_sequenceinfo.stat.csv","filename":"hcv1a_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:25.491000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000351/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000351/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T10:24:22.090435","modified":"2024-05-17T11:23:57.262Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Sequence Info (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11108] UniProtKB protein sequence information that includes sequence version fasta header for the hcv1b accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"675cd4013c0d2b6b8faf9c72cdefbfc2b174d371f2b9eb808e006aa95a2161e6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_sequenceinfo.csv","filename":"hcv1b_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_sequenceinfo.stat.csv","filename":"hcv1b_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":384,"last_update":"2024-05-17T11:23:57.262832Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000351/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000351/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T10:24:22.090435","modified":"2022-09-26T09:05:27.640535","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_sequenceinfo.csv","filename":"hcv1b_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Sequence Info (UniProtKB) dataset contains hcv1b [taxid:11108] UniProtKB protein sequence information that includes sequence version fasta header for the hcv1b accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8070a4ca353a8a3d1cd3b1303c1112d322b9ae34604d8467ca07680b25a929b6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_sequenceinfo.csv","filename":"hcv1b_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_sequenceinfo.stat.csv","filename":"hcv1b_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.881000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000351/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000351/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T10:24:22.090435","modified":"2022-09-26T09:05:27.640535","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_sequenceinfo.csv","filename":"hcv1b_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Sequence Info (UniProtKB) dataset contains hcv1b [taxid:11108] UniProtKB protein sequence information that includes sequence version fasta header for the hcv1b accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"3686a6524e4b54b84dd701b12c7eb7af","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_sequenceinfo.csv","filename":"hcv1b_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_sequenceinfo.stat.csv","filename":"hcv1b_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:25.682000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000352/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000352/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T10:29:16.162139","modified":"2024-05-17T11:23:57.302Z","version":"v-0.0.0"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a EBI-UniProtKB NT file contains proteome data for Hepatitis C virus (isolate H77) [taxid:63746] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"cb1bc0dd596d0a6f175a03b67fd68ae0b5c8b314b7b46b00353fe51527835182","io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_ntdata.nt","filename":"hcv1a_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_ntdata.stat.csv","filename":"hcv1a_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":291,"last_update":"2024-05-17T11:23:57.302257Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000352/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000352/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T10:29:16.162139","modified":"2022-09-26T09:05:27.729530","version":"v-2.0.2"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/hcv1a_protein_ntdata.nt","filename":"hcv1a_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) EBI-UniProtKB NT file contains proteome data for hcv1a [taxid:11108] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"6d829eb09f109ef781065476e46a32900e14909c52d765bb48d29f6c56407492","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_ntdata.nt","filename":"hcv1a_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_ntdata.stat.csv","filename":"hcv1a_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.644000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000352/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000352/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T10:29:16.162139","modified":"2022-09-26T09:05:27.729530","version":"v-2.1.1"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/hcv1a_protein_ntdata.nt","filename":"hcv1a_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) EBI-UniProtKB NT file contains proteome data for hcv1a [taxid:11108] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"756f5b51304c070ac13508b309622e92","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_ntdata.nt","filename":"hcv1a_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_ntdata.stat.csv","filename":"hcv1a_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:25.864000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000353/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000353/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T10:34:27.467680","modified":"2024-05-17T11:23:57.340Z","version":"v-0.0.0"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) EBI-UniProtKB NT file contains proteome data for Hepatitis C virus (isolate Japanese) [taxid:11116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"22c843ef17b6a68ce3bf22f1afd950cfe87ee67b425de54e8dd050f90effe707","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_ntdata.nt","filename":"hcv1b_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_ntdata.stat.csv","filename":"hcv1b_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":340,"last_update":"2024-05-17T11:23:57.340128Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000353/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000353/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T10:34:27.467680","modified":"2022-09-26T09:05:27.677960","version":"v-2.0.2"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/hcv1b_protein_ntdata.nt","filename":"hcv1b_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) EBI-UniProtKB NT file contains proteome data for hcv1b [taxid:11116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"af2c2fdfb5297ef2b6ae283218650fe18669135dc96ca4345f4b4d2086b8ac23","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_ntdata.nt","filename":"hcv1b_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_ntdata.stat.csv","filename":"hcv1b_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.748000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000353/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000353/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T10:34:27.467680","modified":"2022-09-26T09:05:27.677960","version":"v-2.1.1"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/hcv1b_protein_ntdata.nt","filename":"hcv1b_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) EBI-UniProtKB NT file contains proteome data for hcv1b [taxid:11116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0964ad7a1df080b1629232545ab3a7e5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_ntdata.nt","filename":"hcv1b_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_ntdata.stat.csv","filename":"hcv1b_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:26.045000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000354/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000354/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T10:50:51.969235","modified":"2024-05-17T11:23:57.399Z","version":"v-0.0.0"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Information dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"07f18370a6ef4e18604142284e2b5daff83373fa2f2546539feb58c79b094fea","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_info_uniprotkb.csv","filename":"hcv1a_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_info_uniprotkb.stat.csv","filename":"hcv1a_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-05-17T11:23:57.399334Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000354/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000354/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T10:50:51.969235","modified":"2022-09-26T09:05:27.764427","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_info_uniprotkb.csv","filename":"hcv1a_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Information dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"a94d8e47c516f0f2c15ba35bb7ef7029fadfdbc844b7ef61d96e3fcc494bf5ae","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_info_uniprotkb.csv","filename":"hcv1a_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_info_uniprotkb.stat.csv","filename":"hcv1a_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.407000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000354/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000354/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T10:50:51.969235","modified":"2022-09-26T09:05:27.764427","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_info_uniprotkb.csv","filename":"hcv1a_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Information dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"b0e52f558807af30ba9abaf84adf1224","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_info_uniprotkb.csv","filename":"hcv1a_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_info_uniprotkb.stat.csv","filename":"hcv1a_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:26.224000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000355/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000355/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T11:25:59.634509","modified":"2024-05-22T14:43:06.082Z","version":"v-0.0.0"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Citations dataset contains publication information for Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"70bedc9a78e9ce7a6e85c71cdadcaf935ede5f39fa65d6973718ec50adbca4a8","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_citations_uniprotkb.stat.csv","filename":"hcv1a_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":436,"last_update":"2024-05-22T14:43:06.082023Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000355/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000355/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T11:25:59.634509","modified":"2022-09-26T09:05:27.741145","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Citations dataset contains publication information for hcv1a [taxid:11108] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/hcv1a_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"5bb59b237492c24d995b83510847dfce73d3ef7911e45eee157de1224a62c694","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_citations_uniprotkb.stat.csv","filename":"hcv1a_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.918000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000355/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000355/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T11:25:59.634509","modified":"2022-09-26T09:05:27.741145","version":"v-2.1.1"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Citations dataset contains publication information for hcv1a [taxid:11108] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/hcv1a_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e0b99f061f3fc8d4f0000e3973e88c30","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_citations_uniprotkb.stat.csv","filename":"hcv1a_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:26.399000Z","access_count":59},{"object_id":"https://biocomputeobject.org/GLY_000356/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000356/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T14:12:07.407873","modified":"2024-05-17T11:23:57.472Z","version":"v-0.0.0"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Citations dataset contains publication information for Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB accessions that includes PMID, journal name, date and author and title. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"dba8c0e544cc7a00081bbd7697bce7ab96599fcc14837116f251b941d4e91b22","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_citations_uniprotkb.stat.csv","filename":"hcv1b_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":341,"last_update":"2024-05-17T11:23:57.472683Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000356/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000356/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T14:12:07.407873","modified":"2022-09-26T09:05:27.618901","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Citations dataset contains publication information for hcv1b [taxid:11116] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f918f837eab4e62abcf7ecf9ae7b6e3867e591f2c4a6b82a34fa1d09adb572af","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_citations_uniprotkb.stat.csv","filename":"hcv1b_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.516000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000356/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000356/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T14:12:07.407873","modified":"2022-09-26T09:05:27.618901","version":"v-2.1.1"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Citations dataset contains publication information for hcv1b [taxid:11116] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"00b6a6c6530c7ab19adc25ad2c09de4b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_citations_uniprotkb.stat.csv","filename":"hcv1b_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:26.591000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000357/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000357/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T14:22:38.820189","modified":"2024-05-21T13:54:32.540Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Hepatitis C virus (isolate H77) [taxid:63746] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"9070e74e6b27ef0295d57f980603d551266f8aff515ac63616a474ce41a9e648","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_recnames.csv","filename":"hcv1a_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_recnames.stat.csv","filename":"hcv1a_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":244,"last_update":"2024-05-21T13:54:32.540068Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000357/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000357/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T14:22:38.820189","modified":"2022-09-26T09:05:27.615451","version":"v-2.0.2"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_recnames.csv","filename":"hcv1a_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for hcv1a [taxid:11108] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"57345a45f0401fcef321298d62c108580dd122db05c848fd573d00cc9d4dbe2f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_recnames.csv","filename":"hcv1a_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_recnames.stat.csv","filename":"hcv1a_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.041000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000357/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000357/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T14:22:38.820189","modified":"2022-09-26T09:05:27.615451","version":"v-2.1.1"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_recnames.csv","filename":"hcv1a_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for hcv1a [taxid:11108] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"ce794396b770e93c689fbc78f9e87969","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_recnames.csv","filename":"hcv1a_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_recnames.stat.csv","filename":"hcv1a_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:26.784000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000358/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000358/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-13T14:29:13.567811","modified":"2024-05-21T13:55:13.624Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Hepatitis C virus (isolate Japanese) [taxid:10116] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"49808e6b151fce001b36181ccbc332bc7aa8e9f0e5eae3edec721aadc9a7e95a","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_recnames.csv","filename":"hcv1b_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_recnames.stat.csv","filename":"hcv1b_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":293,"last_update":"2024-05-21T13:55:13.624895Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000358/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000358/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-13T14:29:13.567811","modified":"2022-09-26T09:05:27.776653","version":"v-2.0.2"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_idmapping.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_recnames.csv","filename":"hcv1b_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for hcv1b [taxid:10116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d448fa8d7c6b27100e2c8ba1470f1f4949ca293224028b9f474bb031c88f7be0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_recnames.csv","filename":"hcv1b_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_recnames.stat.csv","filename":"hcv1b_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.418000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000358/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000358/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-13T14:29:13.567811","modified":"2022-09-26T09:05:27.776653","version":"v-2.1.1"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_idmapping.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_recnames.csv","filename":"hcv1b_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for hcv1b [taxid:10116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"b3b38f2b08ecb73c58f6cba72350c9bb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_recnames.csv","filename":"hcv1b_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_recnames.stat.csv","filename":"hcv1b_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:26.977000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000359/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000359/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T15:07:44.343644","modified":"2024-05-17T11:23:57.593Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Hepatitis C virus (isolate H77) [taxid:63746] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"3d540044fb2ccab17eb66ecf1a89598b07dc0475a0f09f78bd2fbae908092146","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_altnames.csv","filename":"hcv1a_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_altnames.stat.csv","filename":"hcv1a_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":243,"last_update":"2024-05-17T11:23:57.593156Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000359/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000359/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T15:07:44.343644","modified":"2022-09-26T09:05:27.732497","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_altnames.csv","filename":"hcv1a_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for hcv1a [taxid:11108] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"c4c732990ee47affe0a94873f5b4f8fbbbc70a8b1600afd35a522c5910686241","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_altnames.csv","filename":"hcv1a_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_altnames.stat.csv","filename":"hcv1a_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.968000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000359/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000359/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T15:07:44.343644","modified":"2022-09-26T09:05:27.732497","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_altnames.csv","filename":"hcv1a_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for hcv1a [taxid:11108] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"40b9d5844a50a74a64df8c864ccee22b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_altnames.csv","filename":"hcv1a_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_altnames.stat.csv","filename":"hcv1a_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:27.182000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000360/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000360/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T15:10:56.943062","modified":"2024-05-17T11:23:57.635Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Hepatitis C virus (isolate Japanese) [taxid:11116] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"0955dea1e98028d69d742e815da1056b60254bd48173fd638eb60df294dc5e4f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_altnames.csv","filename":"hcv1b_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_altnames.stat.csv","filename":"hcv1b_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":292,"last_update":"2024-05-17T11:23:57.635224Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000360/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000360/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T15:10:56.943062","modified":"2022-09-26T09:05:27.629062","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_altnames.csv","filename":"hcv1b_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for hcv1b [taxid:11116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7e2540392cb00f03a49535dd0e3efc46d7f044ff5972daffb3d68bf32146e85b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_altnames.csv","filename":"hcv1b_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_altnames.stat.csv","filename":"hcv1b_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.588000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000360/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000360/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T15:10:56.943062","modified":"2022-09-26T09:05:27.629062","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_altnames.csv","filename":"hcv1b_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for hcv1b [taxid:11116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"725a5ef4905689512744425cbc22daca","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_altnames.csv","filename":"hcv1b_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_altnames.stat.csv","filename":"hcv1b_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:27.373000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000361/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000361/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T15:15:56.229012","modified":"2024-05-17T11:23:57.674Z","version":"v-0.0.0"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The HCV1a Gene Ontology (GO) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"76c90b20d5795accb6f51edf85765332567dcbc314f9405d4041059f917b1848","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_go_annotation.csv","filename":"hcv1a_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_go_annotation.stat.csv","filename":"hcv1a_protein_go_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":282,"last_update":"2024-05-17T11:23:57.674482Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000361/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000361/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T15:15:56.229012","modified":"2022-09-26T09:05:27.605977","version":"v-2.0.2"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_go_annotation.csv","filename":"hcv1a_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Gene Ontology (GO) dataset contains hcv1a [taxid:11108] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"4c8bb3a603a399d15f9d1bed155b6f3b773d005a357d1b460a93a7572ec53329","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_go_annotation.csv","filename":"hcv1a_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_go_annotation.stat.csv","filename":"hcv1a_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.717000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000361/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000361/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T15:15:56.229012","modified":"2022-09-26T09:05:27.605977","version":"v-2.1.1"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_go_annotation.csv","filename":"hcv1a_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Gene Ontology (GO) dataset contains hcv1a [taxid:11108] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"065637242cf8505235a075f9bd6ce1a9","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_go_annotation.csv","filename":"hcv1a_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_go_annotation.stat.csv","filename":"hcv1a_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:27.564000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000362/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000362/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T15:19:44.880963","modified":"2024-05-17T11:23:57.710Z","version":"v-0.0.0"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Gene Ontology (GO) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"88e128175da3797bb359ac6a2b44d6a101b083d4c335dc8f91da17487950d3a7","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_go_annotation.csv","filename":"hcv1b_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_go_annotation.stat.csv","filename":"hcv1b_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-17T11:23:57.710202Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000362/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000362/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T15:19:44.880963","modified":"2022-09-26T09:05:27.773273","version":"v-2.0.2"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_go_annotation.csv","filename":"hcv1b_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Gene Ontology (GO) dataset contains hcv1b [taxid:11116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8f3949a1ab051befd5c09ceb6bf267742c9b910a40a596d40ae28d248a4c9e3a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_go_annotation.csv","filename":"hcv1b_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_go_annotation.stat.csv","filename":"hcv1b_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.153000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000362/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000362/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T15:19:44.880963","modified":"2022-09-26T09:05:27.773273","version":"v-2.1.1"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_go_annotation.csv","filename":"hcv1b_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Gene Ontology (GO) dataset contains hcv1b [taxid:11116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"577ebffacd35ea7a9ebebd6ac55bdacf","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_go_annotation.csv","filename":"hcv1b_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_go_annotation.stat.csv","filename":"hcv1b_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:27.747000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000363/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000363/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T15:22:20.601417","modified":"2024-05-17T11:23:57.747Z","version":"v-0.0.0"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The HCV1a Protein PTM Annotation (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"b8da6298aabf5443f7b55dacd310a7118c2c48fbca777917ac4d117e31177803","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-17T11:23:57.747617Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000363/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000363/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T15:22:20.601417","modified":"2022-09-26T09:05:27.734646","version":"v-2.0.2"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein PTM Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"a1c01bde7559c4bfce57d1daf2f2fc5330c01574edaae8f67a191f02c645a483","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.932000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000363/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000363/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T15:22:20.601417","modified":"2022-09-26T09:05:27.734646","version":"v-2.1.1"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein PTM Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"beceeabc5f4ea074dde8cd911e10867e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:27.938000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000364/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000364/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T15:26:35.442241","modified":"2024-06-03T20:41:16.460Z","version":"v-0.0.0"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein PTM Annotation (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"208225468d28b919651735151ae9c7da8eec208e8c44b4884aa3ba3030d5f161","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":380,"last_update":"2024-06-03T20:41:16.460514Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000364/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000364/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T15:26:35.442241","modified":"2022-09-26T09:05:27.713848","version":"v-2.0.2"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein PTM Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"3e9a1035392acba5f1273a5777b322c19002444f2d5fac18c9ed26e6b24ae70a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.233000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000364/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000364/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T15:26:35.442241","modified":"2022-09-26T09:05:27.713848","version":"v-2.1.1"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein PTM Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"ba47d47d5440cb2c58068b8a049dc191","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:28.125000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000365/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000365/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T15:30:24.048685","modified":"2024-05-17T11:23:57.823Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The HCV1a Protein Enzyme Annotation (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] enzyme annotations for UniProtKB canonical accessions. The dataset contains EC numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"092f798b567121e0782d83e767fb0beeffa9936e173bbad58459390aec544325","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2024-05-17T11:23:57.823867Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000365/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000365/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T15:30:24.048685","modified":"2022-09-26T09:05:27.696446","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Enzyme Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"605968150e30446c01b19f3f658c91d57ed2a83a5dacd20b5f478b55a05c211d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.515000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000365/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000365/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T15:30:24.048685","modified":"2022-09-26T09:05:27.696446","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Enzyme Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"cc70cfef41c4d7c2457dfd2d4fea3745","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:28.314000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000366/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000366/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T16:18:24.887237","modified":"2024-06-03T20:53:41.585Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Enzyme Annotation (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"58793a76d203f32388c5b9a11818e8c100049c042c7bb51ecced204538ea6657","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":386,"last_update":"2024-06-03T20:53:41.585114Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000366/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000366/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T16:18:24.887237","modified":"2022-09-26T09:05:27.651278","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Enzyme Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"af015309d215f5607872beefb126dc5d01adfa40b3ee87f23cc79a84141519f3","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.653000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000366/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000366/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T16:18:24.887237","modified":"2022-09-26T09:05:27.651278","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Enzyme Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"f345ade938fd40494d57a6ff43b4324f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:28.499000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000367/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000367/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:19:20.779869","modified":"2024-06-03T20:42:15.958Z","version":"v-0.0.0"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) (HCV) Protein Site Annotation (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"0245f30f249d972ed2f30dcc3a270fef98920cbcd593db1a43ea9c27e1b48523","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":386,"last_update":"2024-06-03T20:42:15.958823Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000367/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000367/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:19:20.779869","modified":"2022-09-26T09:05:27.647182","version":"v-2.0.2"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) (HCV) Protein Site Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"21e6d1eeb0678403d245a29c75c47575d58b21a9fc13859bb6a9ce9fe1ce3a58","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.513000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000367/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000367/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:19:20.779869","modified":"2022-09-26T09:05:27.647182","version":"v-2.1.1"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) (HCV) Protein Site Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"5ef478f29fc1bdf290b49e0ee10236fd","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:28.693000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000368/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000368/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:27:47.710028","modified":"2024-05-17T11:23:57.941Z","version":"v-0.0.0"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The HCV1a  UniProtKB Xref IntAct dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"6b2f1da8e64b5064fc3630b87a3bbc8beb234c8899408d9a82087a79f9eef4d8","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_intact.csv","filename":"hcv1a_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_intact.stat.csv","filename":"hcv1a_protein_xref_intact.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":548,"last_update":"2024-05-17T11:23:57.941979Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000368/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000368/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:27:47.710028","modified":"2022-09-26T09:05:27.724477","version":"v-2.0.2"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_intact.csv","filename":"hcv1a_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref IntAct dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"0cb0c61713df22be216da01503a6f312df8dc387debde08c84ee76b41bbac5b5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_intact.csv","filename":"hcv1a_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_intact.stat.csv","filename":"hcv1a_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.309000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000368/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000368/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:27:47.710028","modified":"2022-09-26T09:05:27.724477","version":"v-2.1.1"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_intact.csv","filename":"hcv1a_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref IntAct dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"c0c56769cda48d20299b064d1dfd3ad0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_intact.csv","filename":"hcv1a_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_intact.stat.csv","filename":"hcv1a_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:28.876000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000369/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000369/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:29:04.813092","modified":"2024-05-17T11:23:57.979Z","version":"v-0.0.0"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref IntAct dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"a1d7c555fbaa4b4995dd1fa757d5cb6885417cac9f7a72d08ad04b681086926b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_intact.csv","filename":"hcv1b_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_intact.stat.csv","filename":"hcv1b_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":596,"last_update":"2024-05-17T11:23:57.979655Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000369/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000369/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:29:04.813092","modified":"2022-09-26T09:05:27.684347","version":"v-2.0.2"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_intact.csv","filename":"hcv1b_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref IntAct dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"9468887654a756a564917d05bc1b894cd4fa21cf90d51ffc5f3ba352aee8ccc3","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_intact.csv","filename":"hcv1b_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_intact.stat.csv","filename":"hcv1b_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.719000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000369/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000369/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:29:04.813092","modified":"2022-09-26T09:05:27.684347","version":"v-2.1.1"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_intact.csv","filename":"hcv1b_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref IntAct dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"208cf0fad4769c27fa10d0ff176b1256","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_intact.csv","filename":"hcv1b_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_intact.stat.csv","filename":"hcv1b_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:29.069000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000370/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000370/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:34:56.163332","modified":"2024-05-17T11:23:58.017Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniProtKB Xref InterPro contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"4668df2f290a20dcc2eb37fef4bbd6d4d5d40826431854673e66a1ff14877ce8","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_interpro.csv","filename":"hcv1a_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_interpro.stat.csv","filename":"hcv1a_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":484,"last_update":"2024-05-17T11:23:58.017315Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000370/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000370/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:34:56.163332","modified":"2022-09-26T09:05:27.660455","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_interpro.csv","filename":"hcv1a_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref InterPro contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"20b0a33a828a5c0a30e028505ba55544fc37cbb7c790116b0753e4dd13711eb1","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_interpro.csv","filename":"hcv1a_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_interpro.stat.csv","filename":"hcv1a_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.286000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000370/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000370/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:34:56.163332","modified":"2022-09-26T09:05:27.660455","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_interpro.csv","filename":"hcv1a_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref InterPro contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"b334a26731185f059eb468440e422a80","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_interpro.csv","filename":"hcv1a_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_interpro.stat.csv","filename":"hcv1a_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:29.260000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000371/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000371/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:36:25.023947","modified":"2024-05-17T11:23:58.055Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref InterPro contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"6844a12607fabcae5adb5e84377dac35edf02b0d2e5b93df797702b13af19065","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_interpro.csv","filename":"hcv1b_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_interpro.stat.csv","filename":"hcv1b_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":533,"last_update":"2024-05-17T11:23:58.055066Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000371/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000371/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:36:25.023947","modified":"2022-09-26T09:05:27.642838","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_interpro.csv","filename":"hcv1b_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref InterPro contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"8751edaeb3dacba8dd29dcc1916bc43d5ce218eeb395adaa82c8222b648a800a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_interpro.csv","filename":"hcv1b_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_interpro.stat.csv","filename":"hcv1b_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.247000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000371/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000371/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:36:25.023947","modified":"2022-09-26T09:05:27.642838","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_interpro.csv","filename":"hcv1b_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref InterPro contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"c71e92b901e925f1e447d16428b4cfb7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_interpro.csv","filename":"hcv1b_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_interpro.stat.csv","filename":"hcv1b_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:29.450000Z","access_count":48},{"object_id":"https://biocomputeobject.org/GLY_000372/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000372/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:38:53.233399","modified":"2024-05-17T11:23:58.092Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniProtKB Xref PDB contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"13e11075e5069550299e7b1b2d67943079c2b8821ac2f72067efa2e9e58c976a","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_pdb.csv","filename":"hcv1a_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_pdb.stat.csv","filename":"hcv1a_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":407,"last_update":"2024-05-17T11:23:58.092672Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000372/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000372/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:38:53.233399","modified":"2022-09-26T09:05:27.708538","version":"v-2.0.2"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_pdb.csv","filename":"hcv1a_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref PDB contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"68f05469bf23df93eabcd7c823a0a4a5d1b3ac2bbfd2ffc393a5019cd2e28a06","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_pdb.csv","filename":"hcv1a_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_pdb.stat.csv","filename":"hcv1a_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.082000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000372/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000372/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:38:53.233399","modified":"2022-09-26T09:05:27.708538","version":"v-2.1.1"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_pdb.csv","filename":"hcv1a_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref PDB contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"32d23e180fd22f46b799ad294276f62b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_pdb.csv","filename":"hcv1a_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_pdb.stat.csv","filename":"hcv1a_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:29.637000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000373/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000373/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:42:17.307133","modified":"2024-05-17T11:23:58.130Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref PDB contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"237910046e88817e5169228239879fea15d1bab46e7c130770a683bd86d07a10","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_pdb.csv","filename":"hcv1b_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_pdb.stat.csv","filename":"hcv1b_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":456,"last_update":"2024-05-17T11:23:58.130689Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000373/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000373/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:42:17.307133","modified":"2022-09-26T09:05:27.706622","version":"v-2.0.2"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_pdb.csv","filename":"hcv1b_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref PDB contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"18b5f5e5b3a245e895b1b1873594618e45856d94c05be77eae7ec3deae1df921","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_pdb.csv","filename":"hcv1b_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_pdb.stat.csv","filename":"hcv1b_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.244000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000373/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000373/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:42:17.307133","modified":"2022-09-26T09:05:27.706622","version":"v-2.1.1"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_pdb.csv","filename":"hcv1b_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref PDB contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"6738756723f01ac80d6cef1b54e770d0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_pdb.csv","filename":"hcv1b_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_pdb.stat.csv","filename":"hcv1b_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:29.827000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000374/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000374/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:45:09.021420","modified":"2024-05-17T11:23:58.167Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniProtKB Xref Pfam contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"21e11a49e33e6efae48343c4fdead26d53ff83a78c57479addc46525e3ef1839","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_pfam.csv","filename":"hcv1a_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_pfam.stat.csv","filename":"hcv1a_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":406,"last_update":"2024-05-17T11:23:58.167841Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000374/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000374/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:45:09.021420","modified":"2022-09-26T09:05:27.767922","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_pfam.csv","filename":"hcv1a_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"3f8ed457ff86a0cdb55445916c93a1de65e987620ed5c0fa42933b08f1ff8b53","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_pfam.csv","filename":"hcv1a_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_pfam.stat.csv","filename":"hcv1a_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.231000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000374/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000374/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:45:09.021420","modified":"2022-09-26T09:05:27.767922","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_pfam.csv","filename":"hcv1a_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"0361dbf679d1d702ecacf8e7e5e22518","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_pfam.csv","filename":"hcv1a_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_pfam.stat.csv","filename":"hcv1a_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:30.020000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000375/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000375/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-14T17:48:55.153656","modified":"2024-05-17T11:23:58.203Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"503d455959a6b55f0c4471b1c50f0b3854ab3e59a52fcea2744cfd0f5a13cce7","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_pfam.csv","filename":"hcv1b_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_pfam.stat.csv","filename":"hcv1b_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":455,"last_update":"2024-05-17T11:23:58.203913Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000375/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000375/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-14T17:48:55.153656","modified":"2022-09-26T09:05:27.738568","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_pfam.csv","filename":"hcv1b_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"bffe996fc2f1d75a842ad794febba64a652c4f5466773c4a1ad274367beae7c6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_pfam.csv","filename":"hcv1b_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_pfam.stat.csv","filename":"hcv1b_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.216000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000375/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000375/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-14T17:48:55.153656","modified":"2022-09-26T09:05:27.738568","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_pfam.csv","filename":"hcv1b_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"3dec0aef5110447d5efdba4d517a6703","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_pfam.csv","filename":"hcv1b_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_pfam.stat.csv","filename":"hcv1b_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:30.211000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000376/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000376/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref euHCVdb","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T11:47:10.216940","modified":"2024-05-17T11:23:58.242Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniProtKB Xref Pfam contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"etag":"b1da4565f3e3bed92cc28e77b4401f9403114ec541ebde08aad9583beff13050","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_euhcvdb.csv","filename":"hcv1a_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_euhcvdb.stat.csv","filename":"hcv1a_protein_xref_euhcvdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":387,"last_update":"2024-05-17T11:23:58.242102Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000376/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000376/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref euHCVdb","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T11:47:10.216940","modified":"2022-09-26T09:05:27.632967","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_euhcvdb.csv","filename":"hcv1a_protein_xref_euhcvdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"etag":"db0df1d9c7bd630f25898791c496016090302225026709bac45177ca8fc1460e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_euhcvdb.csv","filename":"hcv1a_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_euhcvdb.stat.csv","filename":"hcv1a_protein_xref_euhcvdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:53.573000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000376/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000376/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref euHCVdb","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T11:47:10.216940","modified":"2022-09-26T09:05:27.632967","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_euhcvdb.csv","filename":"hcv1a_protein_xref_euhcvdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"etag":"6ed969c59adcd8cb3b6e4b1521b30c86","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_euhcvdb.csv","filename":"hcv1a_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_euhcvdb.stat.csv","filename":"hcv1a_protein_xref_euhcvdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:30.405000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000377/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000377/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref euHCVdb","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T11:48:39.326362","modified":"2024-06-03T20:54:14.884Z","version":"v-0.0.0"},"description_domain":{"keywords":["euHCVdb","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"etag":"9420acab4f1e063b11435ea125785ea379e72a62af6e84b42463bf4f5745f5b2","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_euhcvdb.csv","filename":"hcv1b_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_euhcvdb.stat.csv","filename":"hcv1b_protein_xref_euhcvdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":436,"last_update":"2024-06-03T20:54:14.884684Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000377/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000377/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref euHCVdb","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T11:48:39.326362","modified":"2022-09-26T09:05:27.598181","version":"v-2.0.2"},"description_domain":{"keywords":["euHCVdb","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_euhcvdb.csv","filename":"hcv1b_protein_xref_euhcvdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"etag":"fa283129ff1d70041677d1531844ab56d6c9ce693fdc3656e5c35113915b656f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_euhcvdb.csv","filename":"hcv1b_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_euhcvdb.stat.csv","filename":"hcv1b_protein_xref_euhcvdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.245000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000377/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000377/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref euHCVdb","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T11:48:39.326362","modified":"2022-09-26T09:05:27.598181","version":"v-2.1.1"},"description_domain":{"keywords":["euHCVdb","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_euhcvdb.csv","filename":"hcv1b_protein_xref_euhcvdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"etag":"6ddab6566e158f39c93c9c6a9afe0000","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_euhcvdb.csv","filename":"hcv1b_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_euhcvdb.stat.csv","filename":"hcv1b_protein_xref_euhcvdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:30.602000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000378/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000378/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref ViPR","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T11:59:06.096223","modified":"2024-05-17T11:23:58.322Z","version":"v-0.0.0"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to VIrus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniProtKB Xref Virus Pathogen Resource (ViPR) contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"etag":"c20921e394597a5c9d4b2a03067d85037e786998ed57dc29a1e69353d79ef403","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_viruspathogenresource.csv","filename":"hcv1a_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1a_protein_xref_viruspathogenresource.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":715,"last_update":"2024-05-17T11:23:58.322111Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000378/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000378/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref ViPR","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T11:59:06.096223","modified":"2022-09-26T09:05:27.755237","version":"v-2.0.2"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_viruspathogenresource.csv","filename":"hcv1a_protein_xref_viruspathogenresource.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to VIrus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Virus Pathogen Resource (ViPR) contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"etag":"459f25e769be0e8b5c6ae1418f1cc46b0c3ec362728ef8a7b5e1e9dd3f53b810","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_viruspathogenresource.csv","filename":"hcv1a_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1a_protein_xref_viruspathogenresource.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.042000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000378/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000378/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref ViPR","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T11:59:06.096223","modified":"2023-09-12T21:24:00","version":"v-2.1.1"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_viruspathogenresource.csv","filename":"hcv1a_protein_xref_viruspathogenresource.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Virus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Virus Pathogen Resource (ViPR) contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to ViPR database accessions/identifiers.","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"etag":"852cfd328a390b9640c5a1952d89de1db6128e9b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_viruspathogenresource.csv","filename":"hcv1a_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1a_protein_xref_viruspathogenresource.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-09-12T21:24:12.060000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000379/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000379/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref ViPR","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:01:51.641730","modified":"2024-05-17T11:23:58.360Z","version":"v-0.0.0"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to VIrus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Virus Pathogen Resource contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"etag":"f20f9d0879dea091fd7600d359d297def0a725e15af7673035c93e793137a4e6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_viruspathogenresource.csv","filename":"hcv1b_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1b_protein_xref_viruspathogenresource.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":757,"last_update":"2024-05-17T11:23:58.360554Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000379/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000379/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref ViPR","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:01:51.641730","modified":"2022-09-26T09:05:27.751755","version":"v-2.0.2"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_viruspathogenresource.csv","filename":"hcv1b_protein_xref_viruspathogenresource.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to VIrus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Virus Pathogen Resource contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"etag":"d7f061e0d029291be7ddd11a2b940aa40809418aa6551447dbcf76b0d64c8d9c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_viruspathogenresource.csv","filename":"hcv1b_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1b_protein_xref_viruspathogenresource.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.121000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000379/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000379/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref ViPR","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:01:51.641730","modified":"2023-09-12T21:22:53","version":"v-2.1.1"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_viruspathogenresource.csv","filename":"hcv1b_protein_xref_viruspathogenresource.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Virus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Virus Pathogen Resource contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to ViPR database accessions/identifiers.","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"etag":"a9e3656800cb546de6bd027468264aa3cd60fcc8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_viruspathogenresource.csv","filename":"hcv1b_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1b_protein_xref_viruspathogenresource.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-09-12T21:22:56.535000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000380/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000380/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Hepatitis C Online","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:06:19.473408","modified":"2024-05-17T11:23:58.397Z","version":"v-0.0.0"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniProtKB Xref Pfam contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"3116bef9a01af883dc4ef6783d42d8e69a1f9451178692c5905eb8f7c4f03315","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_hepatitisconline.csv","filename":"hcv1a_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_hepatitisconline.stat.csv","filename":"hcv1a_protein_xref_hepatitisconline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":420,"last_update":"2024-05-17T11:23:58.397585Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000380/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000380/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Hepatitis C Online","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:06:19.473408","modified":"2022-09-26T09:05:27.746688","version":"v-2.0.2"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_hepatitisconline.csv","filename":"hcv1a_protein_xref_hepatitisconline.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"037c05b9dbebb20dc66fd14c3af616b2c5e216dfd676495234aade1f36699ca0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_hepatitisconline.csv","filename":"hcv1a_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_hepatitisconline.stat.csv","filename":"hcv1a_protein_xref_hepatitisconline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.680000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000380/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000380/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Hepatitis C Online","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:06:19.473408","modified":"2022-09-26T09:05:27.746688","version":"v-2.1.1"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_hepatitisconline.csv","filename":"hcv1a_protein_xref_hepatitisconline.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"5d751b200aaffc3d5d261804f4747b2f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_hepatitisconline.csv","filename":"hcv1a_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_hepatitisconline.stat.csv","filename":"hcv1a_protein_xref_hepatitisconline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:31.193000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000381/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000381/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Hepatitis C Online","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:07:34.129887","modified":"2024-05-17T11:23:58.435Z","version":"v-0.0.0"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"264270ebf53ed7c96cb361ad29e62b55572844f0547cccc3b03697081822a7ce","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_hepatitisconline.csv","filename":"hcv1b_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_hepatitisconline.stat.csv","filename":"hcv1b_protein_xref_hepatitisconline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":469,"last_update":"2024-05-17T11:23:58.435778Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000381/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000381/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Hepatitis C Online","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:07:34.129887","modified":"2022-09-26T09:05:27.758776","version":"v-2.0.2"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_hepatitisconline.csv","filename":"hcv1b_protein_xref_hepatitisconline.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"7e2bb4521a16628f76af7affef820347a37836306d9b3ed94e71bb155100bdfb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_hepatitisconline.csv","filename":"hcv1b_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_hepatitisconline.stat.csv","filename":"hcv1b_protein_xref_hepatitisconline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.068000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000381/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000381/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Hepatitis C Online","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:07:34.129887","modified":"2022-09-26T09:05:27.758776","version":"v-2.1.1"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_hepatitisconline.csv","filename":"hcv1b_protein_xref_hepatitisconline.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"501550b0e57b21828cf6c2493386ba5c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_hepatitisconline.csv","filename":"hcv1b_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_hepatitisconline.stat.csv","filename":"hcv1b_protein_xref_hepatitisconline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:31.388000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000382/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000382/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:24:50.340202","modified":"2024-05-17T11:23:58.472Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Glycosylation Sites (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"7430c9ac12f6f00b92328f5011badb197f7019c26fa126ef926a33d861461aee","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-05-17T11:23:58.472930Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000382/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000382/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:24:50.340202","modified":"2022-09-26T09:05:27.609053","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Glycosylation Sites (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f9c632002e228e31e560451c869117fdcaeb389c32b9ebc885d7cdd1fb7a1df7","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.368000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000382/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000382/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:24:50.340202","modified":"2022-09-26T09:05:27.609053","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Glycosylation Sites (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1d8df08cfa579593fdffa6937096547a","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:31.583000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000383/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000383/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:27:03.522584","modified":"2024-05-17T11:23:58.513Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Glycosylation Sites (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"6938e3d9830d55585ca4fec172b762c09ead57595d5a6e26632a6f3925f0eb04","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":362,"last_update":"2024-05-17T11:23:58.513414Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000383/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000383/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:27:03.522584","modified":"2022-09-26T09:05:27.624980","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Glycosylation Sites (UniProtKB) dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1dc7d4037563015deca189c401f1df9b5298859beb57b38a227db54956a964b4","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.004000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000383/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000383/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:27:03.522584","modified":"2022-09-26T09:05:27.624980","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Glycosylation Sites (UniProtKB) dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d13a9d267d2b621c28bcc2157c3dd6cf","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:31.773000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000384/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000384/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:29:48.651730","modified":"2024-05-17T11:23:58.554Z","version":"v-0.0.0"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The HCV1a Phosphorylation Sites (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"8bb80769efb5934d734ac765f30d25cee047609fbbbf7d027a174a19498bf645","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":330,"last_update":"2024-05-17T11:23:58.554288Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000384/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000384/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:29:48.651730","modified":"2022-09-26T09:05:27.636699","version":"v-2.0.2"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Phosphorylation Sites (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7ded4a5371fce7a81655ef99f4049350f7aea16755bb27a1e4ea1803f7d4370c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.519000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000384/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000384/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:29:48.651730","modified":"2022-09-26T09:05:27.636699","version":"v-2.1.1"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Phosphorylation Sites (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"a5f94a3a538811229a7c357e4594ef30","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:31.957000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000385/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000385/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:31:46.752443","modified":"2024-05-17T11:23:58.593Z","version":"v-0.0.0"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Phosphorylation Sites (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"cbb3efd1e104e3949780f1c523fa493d860e76d7b7c6f0d687d0d57122a58d3f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":379,"last_update":"2024-05-17T11:23:58.593514Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000385/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000385/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:31:46.752443","modified":"2022-09-26T09:05:27.669875","version":"v-2.0.2"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Phosphorylation Sites (UniProtKB) dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"6c8144ca2fa3b3228f51cbe32fef6c351dada341158aff8b496a35e7ac49535c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.774000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000385/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000385/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:31:46.752443","modified":"2022-09-26T09:05:27.669875","version":"v-2.1.1"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Phosphorylation Sites (UniProtKB) dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"44cb5b6702a9305dae1af2fe2ca3ea2b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:32.143000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000386/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000386/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:38:06.673108","modified":"2024-05-17T11:23:58.634Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniprotKB Xref BRENDA contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"0228b46eefde740124fc340f5421b6e814f9600bae4b9d4b6fa940e38f511792","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_brenda.csv","filename":"hcv1a_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_brenda.stat.csv","filename":"hcv1a_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":497,"last_update":"2024-05-17T11:23:58.634314Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000386/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000386/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:38:06.673108","modified":"2022-09-26T09:05:27.682352","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_brenda.csv","filename":"hcv1a_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniprotKB Xref BRENDA contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"f2ab373ff64b289c711a93f77e14d20b0fd2d78b2cf86f51e4b54ca4beb69c74","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_brenda.csv","filename":"hcv1a_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_brenda.stat.csv","filename":"hcv1a_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:57.910000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000386/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000386/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref BRENDA","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:38:06.673108","modified":"2022-09-26T09:05:27.682352","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_brenda.csv","filename":"hcv1a_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniprotKB Xref BRENDA contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"etag":"85fbc17a805d4ce6049a3167f9b0823c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_brenda.csv","filename":"hcv1a_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_brenda.stat.csv","filename":"hcv1a_protein_xref_brenda.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:32.340000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000387/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000387/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"94bb60165e5c075dc598683594e4bcb4fcb9889dbd01623ed4211684f8004790","provenance_domain":{"name":"Human Gene Symbols (NCBI RefSeq)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-03-15T12:45:15.358749","modified":"2024-07-12T17:33:17.245Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Human Gene Symbols (NCBI RefSeq) dataset contains Homo sapiens [taxid:9606] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_genenames_refseq.csv","filename":"human_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_genenames_refseq.stat.csv","filename":"human_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":248,"last_update":"2024-07-12T17:33:17.245783Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000387/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000387/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-03-15T12:45:15.358749","modified":"2022-09-26T09:05:27.723156","version":"v-2.0.2"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_genenames_refseq.csv","filename":"human_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Symbols (NCBI RefSeq) dataset contains human [taxid:9606] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"0b87206969002e4b4bc297e18e421c2e2002076bd4e093b2eb7a46f9e54f0a08","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_genenames_refseq.csv","filename":"human_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_genenames_refseq.stat.csv","filename":"human_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.580000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000387/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000387/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:45:15.358749","modified":"2022-09-26T09:05:27.723156","version":"v-2.1.1"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_genenames_refseq.csv","filename":"human_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Symbols (NCBI RefSeq) dataset contains human [taxid:9606] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"a4fecd09895aeaf2ee613e56f0d19304","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_genenames_refseq.csv","filename":"human_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_genenames_refseq.stat.csv","filename":"human_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:32.519000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000388/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000388/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:50:40.430263","modified":"2024-05-17T11:23:58.711Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Symbols (NCBI RefSeq) dataset contains Mus musculus [taxid:10090] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"2bac4f83ed30f4c222e27d3382a4993f90968b78f42ab54518fd38f8ef10c4fe","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_genenames_refseq.csv","filename":"mouse_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_genenames_refseq.stat.csv","filename":"mouse_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":249,"last_update":"2024-05-17T11:23:58.711712Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000388/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000388/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-03-15T12:50:40.430263","modified":"2022-09-26T09:05:27.649522","version":"v-2.0.2"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_genenames_refseq.csv","filename":"mouse_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Symbols (NCBI RefSeq) dataset contains mouse [taxid:10090] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"7127c456acf4f1edce740f97c68baf735fef445b121f51c4dc266db87921d63d","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_genenames_refseq.csv","filename":"mouse_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_genenames_refseq.stat.csv","filename":"mouse_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.241000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000388/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000388/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:50:40.430263","modified":"2022-09-26T09:05:27.649522","version":"v-2.1.1"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_genenames_refseq.csv","filename":"mouse_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Symbols (NCBI RefSeq) dataset contains mouse [taxid:10090] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"414d328d86fb09030dac526cd9db83d1","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genenames_refseq.csv","filename":"mouse_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genenames_refseq.stat.csv","filename":"mouse_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:32.696000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000389/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000389/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:52:59.660127","modified":"2024-05-17T11:23:58.753Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Gene Symbols (NCBI RefSeq) dataset contains Rattus norvegicus [taxid:10116] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"e324b80f4c2b30f5099b8bff6663ba657d21bf76e39befec9e0666cfb9d62f25","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_genenames_refseq.csv","filename":"rat_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_genenames_refseq.stat.csv","filename":"rat_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":252,"last_update":"2024-05-17T11:23:58.753267Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000389/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000389/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-03-15T12:52:59.660127","modified":"2022-09-26T09:05:27.653481","version":"v-2.0.2"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_genenames_refseq.csv","filename":"rat_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Gene Symbols (NCBI RefSeq) dataset contains rat [taxid:10116] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"64eca30dcc0c8cb78243528960b227ca0af70890e9ada39420b8136f080b5ded","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_genenames_refseq.csv","filename":"rat_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_genenames_refseq.stat.csv","filename":"rat_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.112000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000389/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000389/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:52:59.660127","modified":"2022-09-26T09:05:27.653481","version":"v-2.1.1"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_genenames_refseq.csv","filename":"rat_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Gene Symbols (NCBI RefSeq) dataset contains rat [taxid:10116] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"4e55828680a1926b08b1ff7956551cd5","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_genenames_refseq.csv","filename":"rat_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_genenames_refseq.stat.csv","filename":"rat_protein_genenames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:32.906000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000390/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000390/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T12:52:59.660127","modified":"2024-05-17T11:23:58.792Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Rattus norvegicus [taxid:10116] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"b18a8e15b7aa159d11c28dea2f4c76a59f0ae514b0e754a99bd7852c50c8a84c","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_genenames_uniprotkb.csv","filename":"rat_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_genenames_uniprotkb.stat.csv","filename":"rat_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":408,"last_update":"2024-05-17T11:23:58.792452Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000390/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000390/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T12:52:59.660127","modified":"2022-09-26T09:05:27.688694","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_genenames_uniprotkb.csv","filename":"rat_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for rat [taxid:10116] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"60a6df82977abcf93a4ab95b6dfe51f0acc89cc38ba5b2e94ff8f11d91d62a03","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_genenames_uniprotkb.csv","filename":"rat_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_genenames_uniprotkb.stat.csv","filename":"rat_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.808000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000390/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000390/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T12:52:59.660127","modified":"2022-09-26T09:05:27.688694","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_genenames_uniprotkb.csv","filename":"rat_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for rat [taxid:10116] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"08e82f71afbfa4245e537e0f4ab693e4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_genenames_uniprotkb.csv","filename":"rat_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_genenames_uniprotkb.stat.csv","filename":"rat_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:33.088000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000391/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000391/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:08:14.330050","modified":"2024-05-17T11:23:58.830Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Mus musculus [taxid:10090] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"ab73c3e54427a43977700ba3e1edebcb45a5ed53a1c2726e2509b5ea555e7501","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_genenames_uniprotkb.stat.csv","filename":"mouse_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":405,"last_update":"2024-05-17T11:23:58.830839Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000391/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000391/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T13:08:14.330050","modified":"2022-09-26T09:05:27.719599","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for mouse [taxid:10090] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"15b6bdb129cefe03304e96b933438bc2bd0fdd468156a651ecea1b712dc862e8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_genenames_uniprotkb.stat.csv","filename":"mouse_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.372000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000391/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000391/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:08:14.330050","modified":"2022-09-26T09:05:27.719599","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for mouse [taxid:10090] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7f07776e43b65d8734876b014c6f91eb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genenames_uniprotkb.stat.csv","filename":"mouse_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:33.270000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000392/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000392/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:26:46.282740","modified":"2024-05-17T11:23:58.870Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Names (NCBI RefSeq) dataset contains Homo sapiens [taxid:9606] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"ee3ce23ae048f21d876ecea0944a07db80449fc2d1817dbed4d0bb5837ccc514","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_proteinnames_refseq.csv","filename":"human_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_proteinnames_refseq.stat.csv","filename":"human_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":260,"last_update":"2024-05-17T11:23:58.870486Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000392/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000392/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T13:26:46.282740","modified":"2022-09-26T09:05:27.635223","version":"v-2.0.2"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Names (NCBI RefSeq) dataset contains human [taxid:9606] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"b696f0a220fcae431ee412ad065e3e0fe297cbd30271ffab10953e452a37f1f0","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_proteinnames_refseq.csv","filename":"human_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_proteinnames_refseq.stat.csv","filename":"human_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.142000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000392/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000392/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:26:46.282740","modified":"2022-09-26T09:05:27.635223","version":"v-2.1.1"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Names (NCBI RefSeq) dataset contains human [taxid:9606] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"363848a09dc474c4593282c00af9cb76","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_proteinnames_refseq.csv","filename":"human_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_proteinnames_refseq.stat.csv","filename":"human_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:33.455000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000393/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000393/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:29:07.339002","modified":"2024-05-17T11:23:58.910Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Names (NCBI RefSeq) dataset contains Mus musculus [taxid:10090] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"7c9c7b96b4ffa69c7ee8fd01b609a3e38991056ed63b674f1c9d13519b65f3d8","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_proteinnames_refseq.csv","filename":"mouse_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_proteinnames_refseq.stat.csv","filename":"mouse_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":261,"last_update":"2024-05-17T11:23:58.910287Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000393/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000393/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T13:29:07.339002","modified":"2022-09-26T09:05:27.672378","version":"v-2.0.2"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_info_refseq.csv","filename":"mouse_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Names (NCBI RefSeq) dataset contains mouse [taxid:10090] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"55f657e9c9888d485edbcaa90dcc3bae79ff917ade12b5dd0282008a46c8bc8e","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_proteinnames_refseq.csv","filename":"mouse_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_proteinnames_refseq.stat.csv","filename":"mouse_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.415000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000393/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000393/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:29:07.339002","modified":"2022-09-26T09:05:27.672378","version":"v-2.1.1"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_info_refseq.csv","filename":"mouse_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Names (NCBI RefSeq) dataset contains mouse [taxid:10090] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"209065de7d36af6bb66c6ea604cf5663","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_proteinnames_refseq.csv","filename":"mouse_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_proteinnames_refseq.stat.csv","filename":"mouse_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:33.643000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000394/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000394/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2024-05-17T11:23:58.947Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Names (NCBI RefSeq) dataset contains Rattus norvegicus [taxid:10116] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"0944633620c5188c82f65111b758049250ad4260c99129335a5cac2ff9ef6a89","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_proteinnames_refseq.csv","filename":"rat_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_proteinnames_refseq.stat.csv","filename":"rat_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":264,"last_update":"2024-05-17T11:23:58.947623Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000394/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000394/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-03-15T13:32:44.009025","modified":"2022-09-26T09:05:27.607527","version":"v-2.0.2"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Names (NCBI RefSeq) dataset contains rat [taxid:10116] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"88459000ca54465fb4b6235a45b8f97b50017398b25d0ba5327088ba7cc3519a","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_proteinnames_refseq.csv","filename":"rat_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_proteinnames_refseq.stat.csv","filename":"rat_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.809000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000394/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000394/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2022-09-26T09:05:27.607527","version":"v-2.1.1"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Names (NCBI RefSeq) dataset contains rat [taxid:10116] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"70eedf2710d3da5da12954ebb27de455","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_proteinnames_refseq.csv","filename":"rat_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_proteinnames_refseq.stat.csv","filename":"rat_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:33.829000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000395/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000395/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:38:29.540245","modified":"2024-05-17T11:23:58.984Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Homo sapiens [taxid:9606] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"1d181de5e2daa235916094aa0ec7906420609a10fb263a41c9640ec407c4a66f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_submittednames.csv","filename":"human_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_submittednames.stat.csv","filename":"human_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":508,"last_update":"2024-05-17T11:23:58.984930Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000395/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000395/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T13:38:29.540245","modified":"2022-09-26T09:05:27.626904","version":"v-2.0.2"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_submittednames.csv","filename":"human_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for human [taxid:9606] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f49013cf73389635ed9c25f06223f728b58558d2275406cb2007a625587df098","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_submittednames.csv","filename":"human_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_submittednames.stat.csv","filename":"human_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.143000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000395/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000395/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:38:29.540245","modified":"2022-09-26T09:05:27.626904","version":"v-2.1.1"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_submittednames.csv","filename":"human_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for human [taxid:9606] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7e01b49321da5bb5fc7b7b317eb3ea96","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_submittednames.csv","filename":"human_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_submittednames.stat.csv","filename":"human_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:34.019000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000396/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000396/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:39:36.626348","modified":"2024-05-17T11:23:59.022Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Mus musculus [taxid:10090] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"5730a3f0794a2fd9e1ca3aad18c06627074331c89036f212a4ceb79499194fd3","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_submittednames.csv","filename":"mouse_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_submittednames.stat.csv","filename":"mouse_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":509,"last_update":"2024-05-17T11:23:59.022294Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000396/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000396/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T13:39:36.626348","modified":"2022-09-26T09:05:27.749986","version":"v-2.0.2"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_submittednames.csv","filename":"mouse_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for mouse [taxid:10090] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0d7068198a7688820068a1c1fc95600f722d54f62d0b215c8c0beefd0116bc1c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_submittednames.csv","filename":"mouse_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_submittednames.stat.csv","filename":"mouse_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:15.217000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000396/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000396/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:39:36.626348","modified":"2022-09-26T09:05:27.749986","version":"v-2.1.1"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_submittednames.csv","filename":"mouse_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for mouse [taxid:10090] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"fbf8def95aec9fff2b558ff236959187","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_submittednames.csv","filename":"mouse_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_submittednames.stat.csv","filename":"mouse_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:34.209000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000397/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000397/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:43:53.106298","modified":"2024-05-17T11:23:59.062Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Rattus norvegicus [taxid:10116] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"c68a11288dec482d2a8538f4879f96c9c5cbe6ff648960b389b9087b3ba8224b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_submittednames.csv","filename":"rat_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_submittednames.stat.csv","filename":"rat_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":512,"last_update":"2024-05-17T11:23:59.062418Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000397/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000397/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T13:43:53.106298","modified":"2022-09-26T09:05:27.753646","version":"v-2.0.2"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_submittednames.csv","filename":"rat_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for rat [taxid:10116] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot.. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"9dd56735cf4a9d6891f40f80656c68fc6fa3118cbb679bec79c315bd9f4c8040","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_submittednames.csv","filename":"rat_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_submittednames.stat.csv","filename":"rat_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:53.258000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000397/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000397/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Submitted Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:43:53.106298","modified":"2022-09-26T09:05:27.753646","version":"v-2.1.1"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_submittednames.csv","filename":"rat_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for rat [taxid:10116] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot.. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"4c326c9289a9fc543861fe36c884a69e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_submittednames.csv","filename":"rat_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_submittednames.stat.csv","filename":"rat_protein_submittednames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:34.394000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000398/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000398/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T14:32:07.364795","modified":"2024-05-17T11:23:59.102Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Sequence Info (UniProtKB) dataset contains Homo sapiens [taxid:9606] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"9031d9b8dd8257121c30884b29d234b1b3ae44de3e24aac16bb2e745158a981b","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_sequenceinfo.csv","filename":"human_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_sequenceinfo.stat.csv","filename":"human_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":272,"last_update":"2024-05-17T11:23:59.102805Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000398/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000398/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T14:32:07.364795","modified":"2022-09-26T09:05:27.600083","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_sequenceinfo.csv","filename":"human_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Sequence Info (UniProtKB) dataset contains human [taxid:9606] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"21fab51cf48804aaecf5486f9890c36249580761d888d581e62d58ff54c87347","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_sequenceinfo.csv","filename":"human_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_sequenceinfo.stat.csv","filename":"human_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.222000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000398/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000398/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T14:32:07.364795","modified":"2022-09-26T09:05:27.600083","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_sequenceinfo.csv","filename":"human_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Protein Sequence Info (UniProtKB) dataset contains human [taxid:9606] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"7f29e0ef7312998c1c55e87bd6243af0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_sequenceinfo.csv","filename":"human_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_sequenceinfo.stat.csv","filename":"human_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:34.580000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000399/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000399/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T14:34:41.443981","modified":"2024-05-17T11:23:59.141Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Sequence Info (UniProtKB) dataset contains Mus musculus [taxid:10090] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"502ece8bb03929f309555a8cf9e0f1b76eaf32d7e7ff47348192304b7d373a03","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_sequenceinfo.csv","filename":"mouse_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_sequenceinfo.stat.csv","filename":"mouse_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":273,"last_update":"2024-05-17T11:23:59.141889Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000399/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000399/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T14:34:41.443981","modified":"2022-09-26T09:05:27.634083","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_sequenceinfo.csv","filename":"mouse_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Sequence Info (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e1cdb29e8d5d37e584532bfa8c77c1accf4dd098bf8b799e61e78e8ea815109f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_sequenceinfo.csv","filename":"mouse_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_sequenceinfo.stat.csv","filename":"mouse_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.671000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000399/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000399/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T14:34:41.443981","modified":"2022-09-26T09:05:27.634083","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_sequenceinfo.csv","filename":"mouse_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Protein Sequence Info (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e0256ff91a71991e11d5571c4d28313c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_sequenceinfo.csv","filename":"mouse_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_sequenceinfo.stat.csv","filename":"mouse_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:34.773000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000400/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000400/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T14:37:18.669955","modified":"2024-05-17T11:23:59.180Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Sequence Info (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"b6e85a173773bed62b5cee19a2cdc59652d93ef794f570374fa68a4a3fa74cc6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_sequenceinfo.csv","filename":"rat_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_sequenceinfo.stat.csv","filename":"rat_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":276,"last_update":"2024-05-17T11:23:59.180127Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000400/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000400/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-15T14:37:18.669955","modified":"2022-09-26T09:05:56.548735","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_sequenceinfo.csv","filename":"rat_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Sequence Info (UniProtKB) dataset contains rat [taxid:10116] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d07279e047ec868654e1b3e1e27a767fcac169bf2b5fe94c7e776ed0f19e2a12","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_sequenceinfo.csv","filename":"rat_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_sequenceinfo.stat.csv","filename":"rat_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.710000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000400/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000400/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T14:37:18.669955","modified":"2022-09-26T09:05:56.548735","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_sequenceinfo.csv","filename":"rat_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Protein Sequence Info (UniProtKB) dataset contains rat [taxid:10116] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"95d44dee1687087d3281f5c152ad57da","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_sequenceinfo.csv","filename":"rat_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_sequenceinfo.stat.csv","filename":"rat_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:34.968000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000401/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000401/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-16T11:26:15.442401","modified":"2024-05-17T11:23:59.217Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Homo sapiens [taxid:9606] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"d2b9b9203245cda32cc40b9b5888b0d9a0a551f9e9e38e162a3cdbd5a4957ce6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_genenames_uniprotkb.stat.csv","filename":"human_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":403,"last_update":"2024-05-17T11:23:59.217362Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000401/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000401/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-16T11:26:15.442401","modified":"2022-09-26T09:05:56.549809","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for human [taxid:9606] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"01d50cf0b4362f50673149f80fb90fcda8668ac6873f903fdce922a6b705cf82","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_genenames_uniprotkb.stat.csv","filename":"human_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.413000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000401/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000401/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-16T11:26:15.442401","modified":"2022-09-26T09:05:56.549809","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for human [taxid:9606] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f8b912b8ab868ae678007789e7e6723b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_genenames_uniprotkb.stat.csv","filename":"human_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:35.160000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000402/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000402/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"HCV1a N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-20T12:43:15.223816","modified":"2024-05-17T11:23:59.254Z","version":"v-0.0.0"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The HCV1a N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"etag":"481553e96e788f7fa4418e5cb89fc736fb650bd84b6fdf1495576a88f0dc1cc7","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_glycosylation_motifs.csv","filename":"hcv1a_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_glycosylation_motifs.stat.csv","filename":"hcv1a_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-17T11:23:59.254915Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000402/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000402/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1a N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-20T12:43:15.223816","modified":"2022-09-26T09:05:56.422490","version":"v-2.0.2"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_glycosylation_motifs.csv","filename":"hcv1a_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for hcv1a [taxid:11108] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"etag":"806939edc82220c48739bfc80390fec62c60d70565c02924030a4000ad9e481f","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_glycosylation_motifs.csv","filename":"hcv1a_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_glycosylation_motifs.stat.csv","filename":"hcv1a_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.203000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000402/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000402/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1a N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-20T12:43:15.223816","modified":"2022-09-26T09:05:56.422490","version":"v-2.1.1"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_glycosylation_motifs.csv","filename":"hcv1a_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for hcv1a [taxid:11108] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"etag":"3ea1598aa7d57af46cdb32030b665304","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_glycosylation_motifs.csv","filename":"hcv1a_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_glycosylation_motifs.stat.csv","filename":"hcv1a_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:35.357000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000403/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000403/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"HCV1b N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-20T12:45:33.474142","modified":"2024-06-03T20:42:39.787Z","version":"v-0.0.0"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"etag":"c81bc04e1f2e0917518145ba1c9f64b6ef7bafff48002bf963c3b781e0a42381","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_glycosylation_motifs.csv","filename":"hcv1b_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_glycosylation_motifs.stat.csv","filename":"hcv1b_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":406,"last_update":"2024-06-03T20:42:39.787068Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000403/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000403/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1b N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-20T12:45:33.474142","modified":"2022-09-26T09:05:56.444192","version":"v-2.0.2"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_glycosylation_motifs.csv","filename":"hcv1b_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for hcv1b [taxid:11116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"etag":"e6cd0cd234e2ad01c69d71573c012e03ee17f69bda46ec82c45340e0d43e1d60","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_glycosylation_motifs.csv","filename":"hcv1b_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_glycosylation_motifs.stat.csv","filename":"hcv1b_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.262000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000403/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000403/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1b N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-20T12:45:33.474142","modified":"2022-09-26T09:05:56.444192","version":"v-2.1.1"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_glycosylation_motifs.csv","filename":"hcv1b_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for hcv1b [taxid:11116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"etag":"945ce8c2589ae41d68e3399da59c8db5","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_glycosylation_motifs.csv","filename":"hcv1b_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_glycosylation_motifs.stat.csv","filename":"hcv1b_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:35.538000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000404/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000404/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pharos cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"Human UniProtKB Xref Pharos","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of New Mexico","contribution":["contributedBy"],"name":"Tudor I Oprea","email":"TOprea@salud.unm.edu"},{"affiliation":"NIH","contribution":["contributedBy"],"name":"Paul Barrett","email":"paul.barrett@nih.gov"},{"affiliation":"NIH/NIGRI","contribution":["contributedBy"],"name":"Ajay Pillai","email":"ajay.pillai3@nih.gov"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-20T14:14:17.733990","modified":"2024-05-17T11:23:59.337Z","version":"v-0.0.0"},"description_domain":{"keywords":["Pharos","Illuminating the Druggable Genome","drug-targeted protein families","G-protein-coupled receptors (GPCRs)","ion channels (ICs)","kinases"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the UniProtKB accessions and protein name from the Pharos API and maps to the GlyGen's UniProtKB canonical accessions (masterlist) to generate a csv dataset. The accessions that are not mapped are logged in the log file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pharos UniProtKB accessions. The data is from Pharos API based on TCRD version 5.4.0. If you use this dataset please provide proper attribution to Pharos and GlyGen","Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes of Health.","The goal of KMC is to develop a comprehensive, integrated knowledge-base for the Druggable Genome (DG) to illuminate the uncharacterized and/or poorly annotated portion of the DG, focusing on three of the most commonly drug-targeted protein families: G-protein-coupled receptors (GPCRs), ion channels (ICs) and kinases","Nguyen, D.-T., Mathias, S. et al, Pharos: Collating Protein Information to Shed Light on the Druggable Genome , Nucl. Acids Res.i>, 2017, 45(D1), D995-D1002. DOI: 10.1093/nar/gkw1072","https://pharos.nih.gov/about"],"etag":"ec19ff35d7d673140988743c66acf7c38a3c7e48a76c4d93f580e5982f5412fb","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pharos.csv","filename":"human_protein_xref_pharos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pharos.stat.csv","filename":"human_protein_xref_pharos.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":981,"last_update":"2024-05-17T11:23:59.337772Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000404/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000404/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pharos cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"Human UniProtKB Xref Pharos","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of New Mexico","contribution":["contributedBy"],"name":"Tudor I Oprea","email":"TOprea@salud.unm.edu"},{"affiliation":"NIH","contribution":["contributedBy"],"name":"Paul Barrett","email":"paul.barrett@nih.gov"},{"affiliation":"NIH/NIGRI","contribution":["contributedBy"],"name":"Ajay Pillai","email":"ajay.pillai3@nih.gov"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-20T14:14:17.733990","modified":"2022-09-26T09:05:56.452067","version":"v-2.0.2"},"description_domain":{"keywords":["Pharos","Illuminating the Druggable Genome","drug-targeted protein families","G-protein-coupled receptors (GPCRs)","ion channels (ICs)","kinases"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/pharos_protein_all_9606.json","filename":"pharos_protein_all_9606.json"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_pharos.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB accessions and protein name from the Pharos API and maps to the GlyGen's UniProtKB canonical accessions (masterlist) to generate a csv dataset. The accessions that are not mapped are logged in the log file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pharos UniProtKB accessions. The data is from Pharos API based on TCRD version 5.4.0. If you use this dataset please provide proper attribution to Pharos and GlyGen","Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes of Health.","The goal of KMC is to develop a comprehensive, integrated knowledge-base for the Druggable Genome (DG) to illuminate the uncharacterized and/or poorly annotated portion of the DG, focusing on three of the most commonly drug-targeted protein families: G-protein-coupled receptors (GPCRs), ion channels (ICs) and kinases","Nguyen, D.-T., Mathias, S. et al, Pharos: Collating Protein Information to Shed Light on the Druggable Genome , Nucl. Acids Res.i>, 2017, 45(D1), D995-D1002. DOI: 10.1093/nar/gkw1072","https://pharos.nih.gov/about"],"etag":"ee15e456ad1b988a87846cfee67021c6bb272b5c2bf00554e8b8d7a748bb0532","io_domain":{"input_subdomain":[{"uri":{"filename":"batch.10.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.10.json"}},{"uri":{"filename":"batch.11.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.11.json"}},{"uri":{"filename":"batch.12.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.12.json"}},{"uri":{"filename":"batch.13.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.13.json"}},{"uri":{"filename":"batch.14.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.14.json"}},{"uri":{"filename":"batch.15.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.15.json"}},{"uri":{"filename":"batch.16.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.16.json"}},{"uri":{"filename":"batch.17.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.17.json"}},{"uri":{"filename":"batch.18.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.18.json"}},{"uri":{"filename":"batch.19.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.19.json"}},{"uri":{"filename":"batch.1.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.1.json"}},{"uri":{"filename":"batch.20.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.20.json"}},{"uri":{"filename":"batch.21.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.21.json"}},{"uri":{"filename":"batch.2.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.2.json"}},{"uri":{"filename":"batch.3.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.3.json"}},{"uri":{"filename":"batch.4.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.4.json"}},{"uri":{"filename":"batch.5.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.5.json"}},{"uri":{"filename":"batch.6.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.6.json"}},{"uri":{"filename":"batch.7.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.7.json"}},{"uri":{"filename":"batch.8.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.8.json"}},{"uri":{"filename":"batch.9.json","uri":"https:/data.glygen.org/ln2downloads/pharos/03_2020/batch.9.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pharos.csv","filename":"human_protein_xref_pharos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pharos.stat.csv","filename":"human_protein_xref_pharos.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.092000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000404/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000404/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pharos cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"Human UniProtKB Xref Pharos","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of New Mexico","contribution":["contributedBy"],"name":"Tudor I Oprea","email":"TOprea@salud.unm.edu"},{"affiliation":"NIH","contribution":["contributedBy"],"name":"Paul Barrett","email":"paul.barrett@nih.gov"},{"affiliation":"NIH/NIGRI","contribution":["contributedBy"],"name":"Ajay Pillai","email":"ajay.pillai3@nih.gov"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-20T14:14:17.733990","modified":"2022-09-26T09:05:56.452067","version":"v-2.1.1"},"description_domain":{"keywords":["Pharos","Illuminating the Druggable Genome","drug-targeted protein families","G-protein-coupled receptors (GPCRs)","ion channels (ICs)","kinases"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/pharos_protein_all_9606.json","filename":"pharos_protein_all_9606.json"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_pharos.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB accessions and protein name from the Pharos API and maps to the GlyGen's UniProtKB canonical accessions (masterlist) to generate a csv dataset. The accessions that are not mapped are logged in the log file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pharos UniProtKB accessions. The data is from Pharos API based on TCRD version 5.4.0. If you use this dataset please provide proper attribution to Pharos and GlyGen","Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes of Health.","The goal of KMC is to develop a comprehensive, integrated knowledge-base for the Druggable Genome (DG) to illuminate the uncharacterized and/or poorly annotated portion of the DG, focusing on three of the most commonly drug-targeted protein families: G-protein-coupled receptors (GPCRs), ion channels (ICs) and kinases","Nguyen, D.-T., Mathias, S. et al, Pharos: Collating Protein Information to Shed Light on the Druggable Genome , Nucl. Acids Res.i>, 2017, 45(D1), D995-D1002. DOI: 10.1093/nar/gkw1072","https://pharos.nih.gov/about"],"etag":"f91a79ea49d5aaba25ef0b99fd333455","io_domain":{"input_subdomain":[{"uri":{"filename":"batch.10.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.10.json"}},{"uri":{"filename":"batch.11.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.11.json"}},{"uri":{"filename":"batch.12.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.12.json"}},{"uri":{"filename":"batch.13.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.13.json"}},{"uri":{"filename":"batch.14.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.14.json"}},{"uri":{"filename":"batch.15.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.15.json"}},{"uri":{"filename":"batch.16.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.16.json"}},{"uri":{"filename":"batch.17.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.17.json"}},{"uri":{"filename":"batch.18.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.18.json"}},{"uri":{"filename":"batch.19.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.19.json"}},{"uri":{"filename":"batch.1.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.1.json"}},{"uri":{"filename":"batch.20.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.20.json"}},{"uri":{"filename":"batch.21.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.21.json"}},{"uri":{"filename":"batch.2.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.2.json"}},{"uri":{"filename":"batch.3.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.3.json"}},{"uri":{"filename":"batch.4.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.4.json"}},{"uri":{"filename":"batch.5.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.5.json"}},{"uri":{"filename":"batch.6.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.6.json"}},{"uri":{"filename":"batch.7.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.7.json"}},{"uri":{"filename":"batch.8.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.8.json"}},{"uri":{"filename":"batch.9.json","uri":"/data/shared/glyds/downloads/pharos/03_2020/batch.9.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pharos.csv","filename":"human_protein_xref_pharos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pharos.stat.csv","filename":"human_protein_xref_pharos.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:35.734000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000405/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000405/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-20T15:53:27.297125","modified":"2024-05-21T15:51:51.606Z","version":"v-0.0.0"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human NCBI Protein Linkouts contains Homo sapiens [taxid:9606] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"etag":"38723ddcc3fd44d3358590a1d960ca4023b9c19015b9ce6e00e205f5040577b0","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_ncbi_linkouts.csv","filename":"human_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_ncbi_linkouts.stat.csv","filename":"human_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":252,"last_update":"2024-05-21T15:51:51.606419Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000405/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000405/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-20T15:53:27.297125","modified":"2022-09-26T09:05:56.492262","version":"v-2.0.2"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_ncbi_linkouts.csv","filename":"human_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human NCBI Protein Linkouts contains human [taxid:9606] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"02376798fa74ea03f9222ed3b3e5abf2fa4f670625bbd7921b958c3cbd111617","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_ncbi_linkouts.csv","filename":"human_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_ncbi_linkouts.stat.csv","filename":"human_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.998000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000405/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000405/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-20T15:53:27.297125","modified":"2022-09-26T09:05:56.492262","version":"v-2.1.1"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_ncbi_linkouts.csv","filename":"human_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human NCBI Protein Linkouts contains human [taxid:9606] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"257ee93fbd0acb6b5cdc87eaa6981025","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_ncbi_linkouts.csv","filename":"human_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_ncbi_linkouts.stat.csv","filename":"human_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:35.922000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000406/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000406/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-20T15:55:38.335185","modified":"2024-05-21T15:51:40.080Z","version":"v-0.0.0"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse NCBI Protein Linkouts contains Mus musculus [taxid:10090] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"etag":"e30ebf030329af9a06c390e1c2f2b2a63ef3a3c57a8f1cc7a2b29affc58748ff","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_ncbi_linkouts.csv","filename":"mouse_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_ncbi_linkouts.stat.csv","filename":"mouse_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":253,"last_update":"2024-05-21T15:51:40.080941Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000406/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000406/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-20T15:55:38.335185","modified":"2022-09-26T09:05:56.501389","version":"v-2.0.2"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_ncbi_linkouts.csv","filename":"mouse_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse NCBI Protein Linkouts contains mouse [taxid:10090] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"0767a5f6d425c99971c7611e1e6fc5279423fd9b25d9f9a363217a6f5ae9e463","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_ncbi_linkouts.csv","filename":"mouse_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_ncbi_linkouts.stat.csv","filename":"mouse_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.649000Z","access_count":37},{"object_id":"https://biocomputeobject.org/GLY_000406/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000406/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-20T15:55:38.335185","modified":"2022-09-26T09:05:56.501389","version":"v-2.1.1"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_ncbi_linkouts.csv","filename":"mouse_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse NCBI Protein Linkouts contains mouse [taxid:10090] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"19393b350a1507eabd5131ab24519843","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_ncbi_linkouts.csv","filename":"mouse_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_ncbi_linkouts.stat.csv","filename":"mouse_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:36.105000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000407/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000407/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-20T15:56:44.646296","modified":"2024-05-21T15:52:11.578Z","version":"v-0.0.0"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Rat NCBI Protein Linkouts contains Rattus norvegicus [taxid:10116] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"etag":"2a5d16d12983b10606366154a54ca8526a98eacf8df12638a9ee278ebecb907a","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_ncbi_linkouts.csv","filename":"rat_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_ncbi_linkouts.stat.csv","filename":"rat_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":256,"last_update":"2024-05-21T15:52:11.578283Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000407/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000407/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-20T15:56:44.646296","modified":"2022-09-26T09:05:56.519333","version":"v-2.0.2"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_ncbi_linkouts.csv","filename":"rat_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat NCBI Protein Linkouts contains rat [taxid:10116] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"a29731fd2edcaf049458ac28987d4488daa17b7864db4f28a973e39310cb1c4c","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_ncbi_linkouts.csv","filename":"rat_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_ncbi_linkouts.stat.csv","filename":"rat_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.053000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000407/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000407/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat NCBI Protein Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-20T15:56:44.646296","modified":"2022-09-26T09:05:56.519333","version":"v-2.1.1"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_ncbi_linkouts.csv","filename":"rat_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat NCBI Protein Linkouts contains rat [taxid:10116] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"6ac5d35b449807fdcd85b5f48893c7e7","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_ncbi_linkouts.csv","filename":"rat_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_ncbi_linkouts.stat.csv","filename":"rat_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:36.292000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000408/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000408/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"protein"},{"category_value":"Images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"gif","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"3D model of SARS-CoV-2 spike glycoprotein (Animated GIF)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-30T14:24:48.403793","modified":"2024-05-17T11:23:59.502Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycoprotein","images"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input animated gif file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as an animated GIF through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"etag":"d4a6c5195221adfae0d8327e2a4384c32044ef4af337d4776a94c139a2aa5e9a","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"gif","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":438,"last_update":"2024-05-17T11:23:59.502126Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000408/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000408/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"protein"},{"category_value":"Images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"gif","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"3D model of SARS-CoV-2 spike glycoprotein (Animated GIF)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-30T14:24:48.403793","modified":"2022-09-26T09:05:56.463918","version":"v-2.0.2"},"description_domain":{"keywords":["Glycoprotein","images"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/source/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}],"prerequisite":[],"description":"The input animated gif file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as an animated GIF through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"etag":"46b45583568769906f79fa0fee94ed25ce91d7ec593cbe96b821e848c43ea4df","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","uri":"https:/data.glygen.org/ln2downloads/covid_media/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}}],"output_subdomain":[{"mediatype":"gif","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.833000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000408/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000408/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"molecule"},{"category_value":"Images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"gif","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"3D model of SARS-CoV-2 spike glycoprotein (Animated GIF)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-30T14:24:48.403793","modified":"2022-09-26T09:05:56.463918","version":"v-2.1.1"},"description_domain":{"keywords":["Glycoprotein","images"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/source/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}],"prerequisite":[],"description":"The input animated gif file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as an animated GIF through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"etag":"54b96cdafc8fc80637ac7bfba663fb2b","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","uri":"/data/shared/glyds/downloads/covid_media/03_30_2020/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}}],"output_subdomain":[{"mediatype":"gif","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:33:30.985000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000409/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000409/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1238e4650fa41adf6cf00269142ab3a1a69bbf8df4e8091d459ab561906e0269","provenance_domain":{"name":"3D model of SARS-CoV-2 spike glycoprotein (Video)","version":"v-0.0.0","created":"2020-03-31T12:11:20.452848","modified":"2024-05-17T11:23:59.545Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as a .mp4 video through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"description_domain":{"keywords":["Glycoprotein","video"],"platform":[],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input video file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"mp4","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"protein"},{"category_value":"Videos","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"mp4","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":435,"last_update":"2024-05-17T11:23:59.545108Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000409/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000409/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"protein"},{"category_value":"Videos","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"mp4","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"3D model of SARS-CoV-2 spike glycoprotein (Video)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdWith"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-03-31T12:11:20.452848","modified":"2022-09-26T09:05:56.482250","version":"v-2.0.2"},"description_domain":{"keywords":["Glycoprotein","video"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/source/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}],"prerequisite":[],"description":"The input video file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as a .mp4 video through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"etag":"51f6ee05142db120c69971c5a95c5419c9eb4e9c232f23ddb9fa92b29c547bf4","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","uri":"https:/data.glygen.org/ln2downloads/covid_media/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}}],"output_subdomain":[{"mediatype":"mp4","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.284000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000409/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000409/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9a63fe8878ba2f2df99541bac4c5563c","provenance_domain":{"name":"3D model of SARS-CoV-2 spike glycoprotein (Video)","version":"v-2.1.1","created":"2020-03-31T12:11:20.452848","modified":"2023-02-15T19:18:30.892Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as a .mp4 video through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"description_domain":{"keywords":["Glycoprotein","video"],"platform":[],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/source/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}],"prerequisite":[],"description":"The input video file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","uri":"/data/shared/glyds/downloads/covid_media/03_30_2020/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}}],"output_subdomain":[{"mediatype":"mp4","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"molecule"},{"category_value":"Videos","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"mp4","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:33:31.163000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000410/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000410/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Saccharomyces cerevisiae S288C"},{"category_name":"species","category_value":"Hepatitis C virus (isolate Japanese)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-UniProtKB Crossreferences","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"GlyGen-UniProtKB Cross References Mapping","version":"v-0.0.0","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2020-04-01T12:08:42.022917","modified":"2024-05-17T11:23:59.583Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["UniProtKB","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The GlyGen-UniProtKB Cross References dataset contains UniProtKB glycoprotein accessions for the purpose of UniProtKB to GlyGen cross references. In the dataset, the UniProtKB glycoprotein accessions have corresponding glycosylation annotation present in the datasets. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen."],"etag":"42675fe47adb5812b59920bd18c4b191c08439dfb6072a5f4c37d68a1498d374","io_domain":{"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_uniprotkb_xref_mapping.stat.csv","filename":"protein_glygen_uniprotkb_xref_mapping.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":563,"last_update":"2024-05-17T11:23:59.583935Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000410/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000410/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-UniProtKB Crossreferences","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"GlyGen-UniProtKB Crossreferences Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-01T12:08:42.022917","modified":"2022-09-26T09:05:56.496595","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The GlyGen-UniProtKB Crossreferences dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of UniProtKB to GlyGen crossreferences. In the dataset, the UniProtKB glycoprotein accessions have corresponding glycosylation annotation present in the datasets. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen"],"etag":"6e3ca991d179449664fe27d7f7f26362a207d124ed06ff4f4da96e9cf8f5e4da","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.stat.csv","filename":"protein_glygen_uniprotkb_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.518000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000410/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000410/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-UniProtKB Crossreferences","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (genotype 1a, isolate H)"},{"category_name":"species","category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)"}]}}],"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"GlyGen-UniProtKB Crossreferences Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-01T12:08:42.022917","modified":"2023-09-11T23:02:16","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The GlyGen-UniProtKB Crossreferences dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of UniProtKB to GlyGen crossreferences. In the dataset, the UniProtKB glycoprotein accessions have corresponding glycosylation annotation present in the datasets. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen"],"etag":"605c6ab2c3d5a5d3358661b06136be23fab5c8c2","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_uniprotkb_xref_mapping.stat.csv","filename":"protein_glygen_uniprotkb_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-09-11T23:02:18.892000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000411/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000411/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Isoform sequences (UniProtKB)","version":"v-0.0.0","license":"MIT","created":"2020-04-02T22:29:05.258509","modified":"2024-06-03T21:06:36.002Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Isoform sequences (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus  [taxid:694009] protein fasta sequences for the sarscov1 isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"af944dc9e70ebd099ff511bacda5b297c457c6c9464aca8d5e6ad3fd67e9070c","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_allsequences.stat.csv","filename":"sarscov1_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":339,"last_update":"2024-06-03T21:06:36.002909Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000411/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000411/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T22:29:05.258509","modified":"2022-09-26T09:05:56.524822","version":"v-2.0.2"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Isoform sequences (UniProtKB) dataset contains sarscov1 [taxid:694009] protein fasta sequences for the sarscov1 isoform accessions from the UniProtKB database. The dataset is derived from 2020_01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"b7a29b588f7e6477059e77adf5a971f91e2deffadc52053460ce023ebab67e61","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_allsequences.stat.csv","filename":"sarscov1_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.440000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000411/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000411/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Isoform sequences (UniProtKB)","version":"v-2.1.1","license":"MIT","created":"2020-04-02T22:29:05.258509","modified":"2022-09-26T09:05:56.524822","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Isoform sequences (UniProtKB) dataset contains sarscov1 [taxid:694009] protein fasta sequences for the sarscov1 isoform accessions from the UniProtKB database. The dataset is derived from 2020_01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"244ae0933447a4ea5e0a3715eb9273c7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_allsequences.stat.csv","filename":"sarscov1_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:36.904000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000412/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000412/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-02T22:33:42.595609","modified":"2024-06-03T20:55:33.402Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Isoform sequences (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] protein fasta sequences for the sarscov2 isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"57d041e97b661f2595f41835fdc4e2576995d38fc892046363c351aa01b61729","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_allsequences.stat.csv","filename":"sarscov2_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":346,"last_update":"2024-06-03T20:55:33.402825Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000412/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000412/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T22:33:42.595609","modified":"2022-09-26T09:05:56.456080","version":"v-2.0.2"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Isoform sequences (UniProtKB) dataset contains sarscov2 [taxid:2697049] protein fasta sequences for the sarscov2 isoform accessions from the UniProtKB database. The dataset is derived from 2020_01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"a2d46f26ea7551c16ebc9a98b1b972fa32fff24e0a3272b15c4376d3c09aae50","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_allsequences.stat.csv","filename":"sarscov2_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.814000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000412/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000412/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Isoform sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-02T22:33:42.595609","modified":"2022-09-26T09:05:56.456080","version":"v-2.1.1"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Isoform sequences (UniProtKB) dataset contains sarscov2 [taxid:2697049] protein fasta sequences for the sarscov2 isoform accessions from the UniProtKB database. The dataset is derived from 2020_01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"fe43fd72aca24b43e8f00ad5acd1a155","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_allsequences.stat.csv","filename":"sarscov2_protein_allsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:37.098000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000413/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000413/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"45fce77a00ef9613933ec8cd1c7ca9d3f31cb754314a67543c1b6b15393c25dd","provenance_domain":{"name":"SARS-CoV1 Protein Alternative Name (UniProtKB)","version":"v-0.0.0","license":"MIT","created":"2020-04-02T22:40:11.377827","modified":"2024-06-03T21:10:57.450Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Severe acute respiratory syndrome-related coronavirus [taxid:694009] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_altnames.csv","filename":"sarscov1_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_altnames.stat.csv","filename":"sarscov1_protein_altnames.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":290,"last_update":"2024-06-03T21:10:57.450988Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000413/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000413/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T22:40:11.377827","modified":"2022-09-26T09:05:56.487823","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_altnames.csv","filename":"sarscov1_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for sarscov1 [taxid:694009] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"ec88e89b12b3f614381e9d5672be29934768625a83871dfc8d1440b418983f67","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_altnames.csv","filename":"sarscov1_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_altnames.stat.csv","filename":"sarscov1_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:53.461000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000413/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000413/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"46651ade6f8fefe13ffb39298e936fe5","provenance_domain":{"name":"SARS-CoV1 Protein Alternative Name (UniProtKB)","version":"v-2.1.1","license":"MIT","created":"2020-04-02T22:40:11.377827","modified":"2023-03-31T18:48:36.016Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for sarscov1 [taxid:694009] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_altnames.csv","filename":"sarscov1_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_altnames.csv","filename":"sarscov1_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_altnames.stat.csv","filename":"sarscov1_protein_altnames.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:37.294000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000414/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000414/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Binary Interactions (IntAct)","version":"v-0.0.0","license":"MIT","created":"2020-04-02T22:47:16.534551","modified":"2024-06-03T21:11:15.515Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","input_list":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Binary Interaction (IntAct) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"etag":"400d317acf4102b21b283e2617492a847a0e2d17128cec07c67af2f85a92fa35","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_binary_interactions.csv","filename":"sarscov1_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_binary_interactions.stat.csv","filename":"sarscov1_protein_binary_interactions.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":456,"last_update":"2024-06-03T21:11:15.515358Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000414/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000414/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Binary Interactions (IntAct)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T22:47:16.534551","modified":"2022-09-26T09:05:56.428686","version":"v-2.0.2"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_binary_interactions.csv","filename":"sarscov1_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Binary Interaction (IntAct) dataset contains sarscov1 [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"04c08b9b6bb421174cfc04bd839761ec0d412992b15d292b8e9ca8600001534b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_binary_interactions.csv","filename":"sarscov1_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_binary_interactions.stat.csv","filename":"sarscov1_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.428000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000414/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000414/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Binary Interactions (IntAct)","version":"v-2.1.1","license":"MIT","created":"2020-04-02T22:47:16.534551","modified":"2022-09-26T09:05:56.428686","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_binary_interactions.csv","filename":"sarscov1_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Binary Interaction (IntAct) dataset contains sarscov1 [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"etag":"29c13ec7e4ec4624fceda0196ad5b8fc","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_binary_interactions.csv","filename":"sarscov1_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_binary_interactions.stat.csv","filename":"sarscov1_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:37.481000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000415/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000415/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Canonical sequences (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-02T22:54:47.663774","modified":"2024-06-03T20:28:56.912Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Canonical (UniProtKB) Sequences dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"7dfc98a13210af12525570214963fcfc2c2efd972fdefe960ebbde1e1067541e","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_canonicalsequences.stat.csv","filename":"sarscov1_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":314,"last_update":"2024-06-03T20:28:56.912965Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000415/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000415/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T22:54:47.663774","modified":"2022-09-26T09:05:56.440504","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Canonical (UniProtKB) Sequences dataset contains sarscov1 [taxid:694009] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"454ed64bc12cba0077c2efefb7433c9af314d6c680321c9320a14014b17d3a7a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_canonicalsequences.stat.csv","filename":"sarscov1_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.386000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000415/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000415/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Canonical sequences (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-02T22:54:47.663774","modified":"2022-09-26T09:05:56.440504","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Canonical (UniProtKB) Sequences dataset contains sarscov1 [taxid:694009] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"4b7a7e2e11bd07769b6ca7f905f0236e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_canonicalsequences.stat.csv","filename":"sarscov1_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:37.662000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000416/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000416/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-02T22:58:22.926672","modified":"2024-06-03T20:29:29.719Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Canonical (UniProtKB) Sequences dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"90fad8165a3645bb005dd7973081aaa73a3a57bdc14bd7f88601be12a1a26b3d","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_canonicalsequences.stat.csv","filename":"sarscov2_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":322,"last_update":"2024-06-03T20:29:29.719863Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000416/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000416/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T22:58:22.926672","modified":"2022-09-26T09:05:56.543012","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Canonical (UniProtKB) Sequences dataset contains sarscov2 [taxid:2697049] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"69e63dcec5b6bc9ffbc628392cdf2754eda2cb6136645499c322e81cc0d3baae","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_canonicalsequences.stat.csv","filename":"sarscov2_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.838000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000416/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000416/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Canonical sequences (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-02T22:58:22.926672","modified":"2022-09-26T09:05:56.543012","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Canonical (UniProtKB) Sequences dataset contains sarscov2 [taxid:2697049] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"67005b4fbd2f2884dbadeed4b7370fae","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_canonicalsequences.stat.csv","filename":"sarscov2_protein_canonicalsequences.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:37.852000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000418/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000418/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Citations (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:11:32.482Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Citations dataset contains publication information for Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB accessions that includes PMID, journal name, date and author and title. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"48e2318d7859018189fddc22ee17f145b2203268c12aebc17b8a7af37c73b63d","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_citations_uniprotkb.stat.csv","filename":"sarscov1_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":339,"last_update":"2024-06-03T21:11:32.482745Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000418/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000418/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.411897","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Citations dataset contains publication information for sarscov1 [taxid:694009] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e37399ed6123de76f04a87779c7487a6588deb86853db063e809d96087b81567","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_citations_uniprotkb.stat.csv","filename":"sarscov1_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.255000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000418/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000418/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Citations (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.411897","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Citations dataset contains publication information for sarscov1 [taxid:694009] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"507f40814deae82942e42ad30145eea0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_citations_uniprotkb.stat.csv","filename":"sarscov1_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:38.045000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000419/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000419/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ce9bb9d439399c876adb0e175b5f30d37d7cdcc3661357ce80fb899a6dbf2c17","provenance_domain":{"name":"SARS-CoV1 Protein Enzyme Annotation (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-02T23:20:54.157333","modified":"2024-12-10T19:36:00.307Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Enzyme Annotation (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}],"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":530,"last_update":"2024-12-10T19:36:00.307059Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000419/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000419/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T23:20:54.157333","modified":"2022-09-26T09:05:56.449627","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Enzyme Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"45a40f54730ffbb7d625fb213849031e2d533cde3760b59c28de0cdaa2639055","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.829000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000419/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000419/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Enzyme Annotation (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-02T23:20:54.157333","modified":"2022-09-26T09:05:56.449627","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Enzyme Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"d5701cc856da78cbe237737ec1c8e866","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:38.235000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000420/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000420/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-02T23:34:46.503960","modified":"2024-05-17T11:23:59.939Z","version":"v-0.0.0"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Enzyme Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"8110f8f2f62532eae3c3440f0558f95b269b3a20e59952879ad35ce3aeb9560f","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":407,"last_update":"2024-05-17T11:23:59.939699Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000420/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000420/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T23:34:46.503960","modified":"2022-09-26T09:05:56.533134","version":"v-2.0.2"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Enzyme Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"6f2ed5e43d6b5e43277e926eedc888685b04fc417516246860b9f97c1cdcdd81","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.568000Z","access_count":36},{"object_id":"https://biocomputeobject.org/GLY_000420/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000420/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Enzyme Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-02T23:34:46.503960","modified":"2022-09-26T09:05:56.533134","version":"v-2.1.1"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Enzyme Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"3f09a1031a28c3f8211c4368c53ebfb5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:38.433000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000421/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000421/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Function (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-02T23:52:06.244702","modified":"2024-06-03T21:11:46.533Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Function (UniProtKB) dataset contains biological function annotation for Severe acute respiratory syndrome-related coronavirus [taxid:694009] protein accesions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"939003be12201b6429cd069eb45f9afe2796ee9c9715953c13b1dfa13c44642c","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_function_uniprotkb.csv","filename":"sarscov1_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_function_uniprotkb.stat.csv","filename":"sarscov1_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":322,"last_update":"2024-06-03T21:11:46.533849Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000421/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000421/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-02T23:52:06.244702","modified":"2022-09-26T09:05:56.561629","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_function_uniprotkb.csv","filename":"sarscov1_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Function (UniProtKB) dataset contains biological function annotation for sarscov1 [taxid:694009] protein accesions from the UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1fb20797785016ec831bb9820bed2776f758afec6b6e713633946d1e93db0524","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_function_uniprotkb.csv","filename":"sarscov1_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_function_uniprotkb.stat.csv","filename":"sarscov1_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.706000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000421/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000421/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Function (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-02T23:52:06.244702","modified":"2022-09-26T09:05:56.561629","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_function_uniprotkb.csv","filename":"sarscov1_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Function (UniProtKB) dataset contains biological function annotation for sarscov1 [taxid:694009] protein accesions from the UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"53d2700444df51bdab8869e04ebcbdf7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_function_uniprotkb.csv","filename":"sarscov1_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_function_uniprotkb.stat.csv","filename":"sarscov1_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:38.627000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000422/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000422/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:12:10.065Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Function (UniProtKB) dataset contains biological function annotation for Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] protein accesions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"de79e2117d4985cc18f50e65e7a090a33117ec1b887ca8f728398164c075d2bc","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_function_uniprotkb.csv","filename":"sarscov2_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_function_uniprotkb.stat.csv","filename":"sarscov2_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":330,"last_update":"2024-06-03T21:12:10.065890Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000422/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000422/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.418557","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_function_uniprotkb.csv","filename":"sarscov2_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Function (UniProtKB) dataset contains biological function annotation for sarscov2 [taxid:2697049] protein accesions from the UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d9c42c6a7d6da5a73e92206ad09777bbdb9148f72bafd4e10841fdd178a1eb75","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_function_uniprotkb.csv","filename":"sarscov2_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_function_uniprotkb.stat.csv","filename":"sarscov2_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.430000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000422/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000422/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.418557","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_function_uniprotkb.csv","filename":"sarscov2_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Function (UniProtKB) dataset contains biological function annotation for sarscov2 [taxid:2697049] protein accesions from the UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"dc6d5ba4c0cfc7cba73c017814b40410","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_function_uniprotkb.csv","filename":"sarscov2_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_function_uniprotkb.stat.csv","filename":"sarscov2_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:38.809000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000425/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000425/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Gene Symbols (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T00:21:52.771924","modified":"2024-05-17T11:24:00.054Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for sarscov1 [taxid:694009] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"9beca309d9173aca395f7578b1df266c6e1af8f701ac85cd6bf8488c329866bb","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_genenames_uniprotkb.csv","filename":"sarscov1_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_genenames_uniprotkb.stat.csv","filename":"sarscov1_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":481,"last_update":"2024-05-17T11:24:00.054453Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000425/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000425/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T00:21:52.771924","modified":"2022-09-26T09:05:56.476005","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_genenames_uniprotkb.csv","filename":"sarscov1_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for sarscov1 [taxid:694009] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"4e1a74e19421f3ffa3db7614cb43f056df7099ee30a474eae41f49109b6e4a6c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_genenames_uniprotkb.csv","filename":"sarscov1_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_genenames_uniprotkb.stat.csv","filename":"sarscov1_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.514000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000425/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000425/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Gene Symbols (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T00:21:52.771924","modified":"2022-09-26T09:05:56.476005","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_genenames_uniprotkb.csv","filename":"sarscov1_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for sarscov1 [taxid:694009] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"85c3c0a306452503f21093938af78d78","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_genenames_uniprotkb.csv","filename":"sarscov1_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_genenames_uniprotkb.stat.csv","filename":"sarscov1_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:39.001000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000426/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000426/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:12:31.133Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Severe acute respiratory syndrome coronavirus 2  [taxid:2697049] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"493e56d9e98c04cb183cccf0de803ed2e2d47db06d71e1d8c578000baa8b1e52","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_genenames_uniprotkb.csv","filename":"sarscov2_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_genenames_uniprotkb.stat.csv","filename":"sarscov2_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":481,"last_update":"2024-06-03T21:12:31.133102Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000426/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000426/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.504356","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_genenames_uniprotkb.csv","filename":"sarscov2_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for sarscov2 [taxid:2697049] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1f48ee4ad50e6385b9282f5c39ed4611b33db255a94f6e6df1aed5a1d6828c43","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_genenames_uniprotkb.csv","filename":"sarscov2_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_genenames_uniprotkb.stat.csv","filename":"sarscov2_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.711000Z","access_count":35},{"object_id":"https://biocomputeobject.org/GLY_000426/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000426/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Symbols (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.504356","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_genenames_uniprotkb.csv","filename":"sarscov2_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for sarscov2 [taxid:2697049] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"2a09d9b2e7f0efd783a9969112f3cbc9","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_genenames_uniprotkb.csv","filename":"sarscov2_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_genenames_uniprotkb.stat.csv","filename":"sarscov2_protein_genenames_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:39.190000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000427/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000427/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T00:35:31.181876","modified":"2024-06-03T21:07:16.510Z","version":"v-0.0.0"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"etag":"365ac74673af9c40436ac9781ff995f84f8d4ae721186642869ccc0dd9b639af","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_glycosylation_motifs.csv","filename":"sarscov1_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_glycosylation_motifs.stat.csv","filename":"sarscov1_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":404,"last_update":"2024-06-03T21:07:16.510094Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000427/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000427/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T00:35:31.181876","modified":"2022-09-26T09:05:56.515555","version":"v-2.0.2"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_glycosylation_motifs.csv","filename":"sarscov1_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for sarscov1 [taxid:694009] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2020_01 UniprotKB release."],"etag":"f45a3b887ba348dde64e0ebe225f1a0d3596470a6a9ad295f609d8e83ce10159","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_glycosylation_motifs.csv","filename":"sarscov1_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_glycosylation_motifs.stat.csv","filename":"sarscov1_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.512000Z","access_count":33},{"object_id":"https://biocomputeobject.org/GLY_000427/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000427/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T00:35:31.181876","modified":"2022-09-26T09:05:56.515555","version":"v-2.1.1"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_glycosylation_motifs.csv","filename":"sarscov1_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for sarscov1 [taxid:694009] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2020_01 UniprotKB release."],"etag":"e2b33f0d00b03795ec6fe875f7a27d60","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_glycosylation_motifs.csv","filename":"sarscov1_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_glycosylation_motifs.stat.csv","filename":"sarscov1_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:39.373000Z","access_count":34},{"object_id":"https://biocomputeobject.org/GLY_000428/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000428/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:07:42.416Z","version":"v-0.0.0"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"etag":"a130114cc02c09f1ae8ab6198a892793ebc78b84bd886d6460e97a7c7caadcf6","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_glycosylation_motifs.csv","filename":"sarscov2_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_glycosylation_motifs.stat.csv","filename":"sarscov2_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":412,"last_update":"2024-06-03T21:07:42.416099Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000428/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000428/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.460056","version":"v-2.0.2"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_glycosylation_motifs.csv","filename":"sarscov2_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for sarscov2 [taxid:2697049] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2020_01 UniprotKB release."],"etag":"6b4caa4e0a443a1b979c3dc7822453903cdc488b38792c2505b5c91f81fef0e5","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_glycosylation_motifs.csv","filename":"sarscov2_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_glycosylation_motifs.stat.csv","filename":"sarscov2_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.586000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000428/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000428/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 N-Glycosylation Sequon","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.460056","version":"v-2.1.1"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_glycosylation_motifs.csv","filename":"sarscov2_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for sarscov2 [taxid:2697049] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2020_01 UniprotKB release."],"etag":"e09223ead56fb8c5e3aca089ef24e3ea","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_glycosylation_motifs.csv","filename":"sarscov2_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_glycosylation_motifs.stat.csv","filename":"sarscov2_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:39.564000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000429/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000429/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Gene Ontology (GO)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:12:51.102Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Ontology (GO) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"ca242a21a812cb4da7a2cecb256fbe67926bdad38cd700b7c1b7e8d75e529d67","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_go_annotation.csv","filename":"sarscov1_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_go_annotation.stat.csv","filename":"sarscov1_protein_go_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":329,"last_update":"2024-06-03T21:12:51.102340Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000429/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000429/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.484478","version":"v-2.0.2"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_go_annotation.csv","filename":"sarscov1_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Ontology (GO) dataset contains sarscov1 [taxid:694009] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"92956728730b9e2a1a282d8cda7af4d8370b0a953a8921105d09513a72999227","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_go_annotation.csv","filename":"sarscov1_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_go_annotation.stat.csv","filename":"sarscov1_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.707000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000429/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000429/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Gene Ontology (GO)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.484478","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":[],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_go_annotation.csv","filename":"sarscov1_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Ontology (GO) dataset contains sarscov1 [taxid:694009] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"f14f0eda196bd95cdbc1e05bff80c079","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_go_annotation.csv","filename":"sarscov1_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_go_annotation.stat.csv","filename":"sarscov1_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:39.748000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000430/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000430/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:13:30.333Z","version":"v-0.0.0"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Ontology (GO) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"fb2903d2792a9c3609855ef38f377da2d428f3d16bfecdbce41bafa1d85e69d9","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_go_annotation.csv","filename":"sarscov2_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_go_annotation.stat.csv","filename":"sarscov2_protein_go_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2024-06-03T21:13:30.333427Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000430/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000430/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.506394","version":"v-2.0.2"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_go_annotation.csv","filename":"sarscov2_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Ontology (GO) dataset contains sarscov2 [taxid:2697049] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"cb885356be38c9327f6dea7519c93c927f58c597b16f6b3bfb73ede0f28275a4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_go_annotation.csv","filename":"sarscov2_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_go_annotation.stat.csv","filename":"sarscov2_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.717000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000430/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000430/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Ontology (GO)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.506394","version":"v-2.1.1"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_go_annotation.csv","filename":"sarscov2_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Ontology (GO) dataset contains sarscov2 [taxid:2697049] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"79f28ea8008783ea2bd869c002ec9876","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_go_annotation.csv","filename":"sarscov2_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_go_annotation.stat.csv","filename":"sarscov2_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:39.938000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000432/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000432/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Information (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:13:54.849Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Information dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"7d0a8f22d5da765a25e216fbe053f55ae684ddb79fd1f315592dfbcf3c9257bf","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_info_uniprotkb.csv","filename":"sarscov1_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_info_uniprotkb.stat.csv","filename":"sarscov1_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2024-06-03T21:13:54.849466Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000432/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000432/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.469860","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_info_uniprotkb.csv","filename":"sarscov1_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Information dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e541408e5e7f7af3916ec5deb064309f6d2828f78ad18c05ce91fbfec447c452","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_info_uniprotkb.csv","filename":"sarscov1_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_info_uniprotkb.stat.csv","filename":"sarscov1_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.634000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000432/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000432/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Information (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.469860","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_info_uniprotkb.csv","filename":"sarscov1_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Information dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"c22baffb319f39637344e1c3327d37f9","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_info_uniprotkb.csv","filename":"sarscov1_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_info_uniprotkb.stat.csv","filename":"sarscov1_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:40.139000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000433/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000433/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:14:21.213Z","version":"v-0.0.0"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Information dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"68122a8bc77cd7a0422fd7da239a56a37a5d3f1caf661896c5287fa2057938bc","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_info_uniprotkb.csv","filename":"sarscov2_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_info_uniprotkb.stat.csv","filename":"sarscov2_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2024-06-03T21:14:21.213895Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000433/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000433/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.477982","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_info_uniprotkb.csv","filename":"sarscov2_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Information dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"16d83027ffad053ff429abf30fa34a4729ab2a795f2be647233a91e852a691e5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_info_uniprotkb.csv","filename":"sarscov2_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_info_uniprotkb.stat.csv","filename":"sarscov2_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.082000Z","access_count":9},{"object_id":"https://biocomputeobject.org/GLY_000433/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000433/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.477982","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_info_uniprotkb.csv","filename":"sarscov2_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Information dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"261f5b06a62c09ea7d48ce2e25c6bcff","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_info_uniprotkb.csv","filename":"sarscov2_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_info_uniprotkb.stat.csv","filename":"sarscov2_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:40.338000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000434/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000434/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:00:44.846784","modified":"2024-06-03T21:14:43.119Z","version":"v-0.0.0"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Proteome Master list dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"a4600ab9ebf06b9ae8b03e81f42c27a361d273e58d866f729479a438a8eb802f","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_masterlist.stat.csv","filename":"sarscov2_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":368,"last_update":"2024-06-03T21:14:43.119424Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000434/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000434/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:00:44.846784","modified":"2022-09-26T09:05:56.416572","version":"v-2.0.2"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Proteome Master list dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"0699668337d14108f70006a399f285d3792848046a082fe5a0b415d5c072aabb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.stat.csv","filename":"sarscov2_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.471000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000434/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000434/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:00:44.846784","modified":"2022-09-26T09:05:56.416572","version":"v-2.1.1"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Proteome Master list dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"bd0ebc0af26c8ec20b99a3ada5cfe3d1","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.stat.csv","filename":"sarscov2_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:40.530000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000435/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000435/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 EBI-UniProtKB NT file","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:15:05.081Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) EBI-UniProtKB NT file contains proteome data for Severe acute respiratory syndrome-related coronavirus [taxid:694009] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"c12e246a915684054bc46f8ab5349a5d246e5ae0036262d1ce34eb2fa4558f61","io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_ntdata.nt","filename":"sarscov1_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_ntdata.stat.csv","filename":"sarscov1_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":338,"last_update":"2024-06-03T21:15:05.081096Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000435/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000435/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.446710","version":"v-2.0.2"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/sarscov1_protein_ntdata.nt","filename":"sarscov1_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) EBI-UniProtKB NT file contains proteome data for sarscov1 [taxid:694009] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"ca30bb0b49b8741e8d1cc1db5235acce975c1e39c56a5429a74df8369b347e77","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_ntdata.nt","filename":"sarscov1_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_ntdata.stat.csv","filename":"sarscov1_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.029000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000435/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000435/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 EBI-UniProtKB NT file","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.446710","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/sarscov1_protein_ntdata.nt","filename":"sarscov1_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) EBI-UniProtKB NT file contains proteome data for sarscov1 [taxid:694009] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"41bbb959e04a2242061ec94d4f78c59c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_ntdata.nt","filename":"sarscov1_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_ntdata.stat.csv","filename":"sarscov1_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:40.726000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000436/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000436/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:15:31.940Z","version":"v-0.0.0"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) EBI-UniProtKB NT file contains proteome data for Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"443ac028ed9c14223e1e661bcdc6c624f23a1aa9518e10b84830b75075c333a5","io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_ntdata.nt","filename":"sarscov2_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_ntdata.stat.csv","filename":"sarscov2_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":346,"last_update":"2024-06-03T21:15:31.940913Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000436/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000436/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.534249","version":"v-2.0.2"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/sarscov2_protein_ntdata.nt","filename":"sarscov2_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) EBI-UniProtKB NT file contains proteome data for sarscov2 [taxid:2697049] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"02cd70f1ca574ab1a9736787630aa90d9db5f3b89b94cdda5fb6dbadeba89637","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_ntdata.nt","filename":"sarscov2_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_ntdata.stat.csv","filename":"sarscov2_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.070000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000436/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000436/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 EBI-UniProtKB NT file","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.534249","version":"v-2.1.1"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/sarscov2_protein_ntdata.nt","filename":"sarscov2_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) EBI-UniProtKB NT file contains proteome data for sarscov2 [taxid:2697049] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1331d4cb0ce93e33bd24f538666fe597","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_ntdata.nt","filename":"sarscov2_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_ntdata.stat.csv","filename":"sarscov2_protein_ntdata.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:40.936000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000437/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000437/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2024-05-17T11:24:00.486Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Names (NCBI RefSeq) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"df135f76e9d8e02b51d444cdcffbc5df48b21a8c8c03e91878a3fb10ce089cad","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_proteinnames_refseq.csv","filename":"sarscov1_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_proteinnames_refseq.stat.csv","filename":"sarscov1_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":327,"last_update":"2024-05-17T11:24:00.486075Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000437/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000437/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-03-15T13:32:44.009025","modified":"2022-09-26T09:05:56.559938","version":"v-2.0.2"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_info_refseq.csv","filename":"sarscov1_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Names (NCBI RefSeq) dataset contains sarscov1 [taxid:694009] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"94ddb4cecb65c2d59c64d4c74228e0d03177886a0b254caf345ac750f7abbf2b","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_proteinnames_refseq.csv","filename":"sarscov1_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_proteinnames_refseq.stat.csv","filename":"sarscov1_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.140000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000437/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000437/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2022-09-26T09:05:56.559938","version":"v-2.1.1"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_info_refseq.csv","filename":"sarscov1_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Names (NCBI RefSeq) dataset contains sarscov1 [taxid:694009] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"5d9f1cbd46c69d9063b280b7e3ff95d2","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_proteinnames_refseq.csv","filename":"sarscov1_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_proteinnames_refseq.stat.csv","filename":"sarscov1_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:41.119000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000438/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000438/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Recommended Names (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2024-05-21T13:58:10.741Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Severe acute respiratory syndrome-related coronavirus [taxid:694009] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"a856e596437a8b5649cbd9d34fdcb237c1a7864163cb4278751eefa22e7001f1","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_recnames.csv","filename":"sarscov1_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_recnames.stat.csv","filename":"sarscov1_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":290,"last_update":"2024-05-21T13:58:10.741231Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000438/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000438/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.431025","version":"v-2.0.2"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_recnames.csv","filename":"sarscov1_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for sarscov1 [taxid:694009] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"5a9cca80d14e593b942e66cf37168dc83a6ad44e22b49b85956685742660926d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_recnames.csv","filename":"sarscov1_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_recnames.stat.csv","filename":"sarscov1_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.299000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000438/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000438/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Recommended Names (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.431025","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_recnames.csv","filename":"sarscov1_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for sarscov1 [taxid:694009] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1939e8451da59534a8c08b399ea4c50f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_recnames.csv","filename":"sarscov1_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_recnames.stat.csv","filename":"sarscov1_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:41.307000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000439/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000439/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-05-21T14:01:47.566Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"61565501274cea3d90400c1e717c0811cf0d20d10bd4755d9ee1fe7f85f4ddef","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_recnames.csv","filename":"sarscov2_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_recnames.stat.csv","filename":"sarscov2_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":298,"last_update":"2024-05-21T14:01:47.566104Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000439/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000439/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.437538","version":"v-2.0.2"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_recnames.csv","filename":"sarscov2_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for sarscov2 [taxid:2697049] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"9e4c0950913bc06c07cab29873431ebc54c59da05d2e872ebd04b453c4f475c9","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_recnames.csv","filename":"sarscov2_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_recnames.stat.csv","filename":"sarscov2_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.302000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000439/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000439/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Recommended Names (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.437538","version":"v-2.1.1"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_recnames.csv","filename":"sarscov2_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for sarscov2 [taxid:2697049] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"3c7d547c76b8782dfab1ff3335d536be","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_recnames.csv","filename":"sarscov2_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_recnames.stat.csv","filename":"sarscov2_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:41.493000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000440/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000440/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Sequence Info (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:15:58.949Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Sequence Info (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"e7e096a5a8ccb6cafbfeb0b9919f144050defd7f6b6d7c65e24a610d1914395d","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_sequenceinfo.csv","filename":"sarscov1_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_sequenceinfo.stat.csv","filename":"sarscov1_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":339,"last_update":"2024-06-03T21:15:58.949066Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000440/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000440/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.552328","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_sequenceinfo.csv","filename":"sarscov1_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Sequence Info (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"25041ac30a106b8bc0be5657ba8506d77156f466055e7de7dcdecb6893293ed4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_sequenceinfo.csv","filename":"sarscov1_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_sequenceinfo.stat.csv","filename":"sarscov1_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.541000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000440/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000440/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Sequence Info (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.552328","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_sequenceinfo.csv","filename":"sarscov1_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Sequence Info (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"0738202f45914ffd82042cdd1d752c21","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_sequenceinfo.csv","filename":"sarscov1_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_sequenceinfo.stat.csv","filename":"sarscov1_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:41.686000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000441/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000441/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:16:19.959Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Sequence Info (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"69ee1f9d82fa69799597d97628e540369182663311894f40e94fdbfca67caf90","io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_sequenceinfo.csv","filename":"sarscov2_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_sequenceinfo.stat.csv","filename":"sarscov2_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":347,"last_update":"2024-06-03T21:16:19.959456Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000441/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000441/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.545371","version":"v-2.0.2"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_sequenceinfo.csv","filename":"sarscov2_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Sequence Info (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"08953300f22cbcbcd07829406bb208bbfe903de6d659dce8a7eccee8e1db2906","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_sequenceinfo.csv","filename":"sarscov2_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_sequenceinfo.stat.csv","filename":"sarscov2_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.902000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000441/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000441/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Sequence Info (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.545371","version":"v-2.1.1"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_sequenceinfo.csv","filename":"sarscov2_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Sequence Info (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"2decd2f2a6a2b3de003d1516d0bee7b7","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_sequenceinfo.csv","filename":"sarscov2_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_sequenceinfo.stat.csv","filename":"sarscov2_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:41.877000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000442/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000442/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Signal Peptide","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2024-06-03T21:16:44.682Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Signal Peptide dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"bd3425600565acffed2e5815a1cc3ea7caf14388204c61c7b9385babfa51da14","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_annotation.csv","filename":"sarscov1_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_peptidesequences.fasta","filename":"sarscov1_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_cleavedsequences.fasta","filename":"sarscov1_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_fullsequences.fasta","filename":"sarscov1_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_annotation.stat.csv","filename":"sarscov1_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_peptidesequences.stat.csv","filename":"sarscov1_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_cleavedsequences.stat.csv","filename":"sarscov1_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_signalp_fullsequences.stat.csv","filename":"sarscov1_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":680,"last_update":"2024-06-03T21:16:44.682579Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000442/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000442/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.441566","version":"v-2.0.2"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_annotation.csv","filename":"sarscov1_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_peptidesequences.fasta","filename":"sarscov1_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_cleavedsequences.fasta","filename":"sarscov1_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_fullsequences.fasta","filename":"sarscov1_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Signal Peptide dataset contains sarscov1 [taxid:694009] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"a102c6c95cb467edb76c406f155d48d8d3c9cef57cd27db7fd308b413b0cbaf1","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_annotation.csv","filename":"sarscov1_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_peptidesequences.fasta","filename":"sarscov1_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_cleavedsequences.fasta","filename":"sarscov1_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_fullsequences.fasta","filename":"sarscov1_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_annotation.stat.csv","filename":"sarscov1_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_peptidesequences.stat.csv","filename":"sarscov1_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_cleavedsequences.stat.csv","filename":"sarscov1_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_signalp_fullsequences.stat.csv","filename":"sarscov1_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.683000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000442/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000442/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Signal Peptide","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T11:46:41.584409","modified":"2022-09-26T09:05:56.441566","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_annotation.csv","filename":"sarscov1_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_peptidesequences.fasta","filename":"sarscov1_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_cleavedsequences.fasta","filename":"sarscov1_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_fullsequences.fasta","filename":"sarscov1_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Signal Peptide dataset contains sarscov1 [taxid:694009] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"f94701fe1e43fe83e1a0fe760b51c857","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_annotation.csv","filename":"sarscov1_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_peptidesequences.fasta","filename":"sarscov1_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_cleavedsequences.fasta","filename":"sarscov1_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_fullsequences.fasta","filename":"sarscov1_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_annotation.stat.csv","filename":"sarscov1_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_peptidesequences.stat.csv","filename":"sarscov1_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_cleavedsequences.stat.csv","filename":"sarscov1_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_signalp_fullsequences.stat.csv","filename":"sarscov1_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:42.057000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000443/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000443/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:48:23.646763","modified":"2024-06-03T21:17:16.126Z","version":"v-0.0.0"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Signal Peptide dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"37e4c21d9767408197cf635fe0c44a69044b35c8fce8785d59bdbd2f5eb15a60","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_annotation.csv","filename":"sarscov2_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_peptidesequences.fasta","filename":"sarscov2_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_cleavedsequences.fasta","filename":"sarscov2_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_fullsequences.fasta","filename":"sarscov2_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_annotation.stat.csv","filename":"sarscov2_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_peptidesequences.stat.csv","filename":"sarscov2_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_cleavedsequences.stat.csv","filename":"sarscov2_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_signalp_fullsequences.stat.csv","filename":"sarscov2_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":688,"last_update":"2024-06-03T21:17:16.126555Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000443/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000443/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:48:23.646763","modified":"2022-09-26T09:05:56.426739","version":"v-2.0.2"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_annotation.csv","filename":"sarscov2_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_peptidesequences.fasta","filename":"sarscov2_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_cleavedsequences.fasta","filename":"sarscov2_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_fullsequences.fasta","filename":"sarscov2_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Signal Peptide dataset contains sarscov2 [taxid:2697049] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"3674ef8042e20d064b9ab51cfc392a254b49a3aecd76d19bb0a98d4bd37291b1","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_annotation.csv","filename":"sarscov2_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_peptidesequences.fasta","filename":"sarscov2_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_cleavedsequences.fasta","filename":"sarscov2_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_fullsequences.fasta","filename":"sarscov2_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_annotation.stat.csv","filename":"sarscov2_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_peptidesequences.stat.csv","filename":"sarscov2_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_cleavedsequences.stat.csv","filename":"sarscov2_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_signalp_fullsequences.stat.csv","filename":"sarscov2_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.485000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000443/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000443/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:48:23.646763","modified":"2022-09-26T09:05:56.426739","version":"v-2.1.1"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_annotation.csv","filename":"sarscov2_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_peptidesequences.fasta","filename":"sarscov2_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_cleavedsequences.fasta","filename":"sarscov2_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_fullsequences.fasta","filename":"sarscov2_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Signal Peptide dataset contains sarscov2 [taxid:2697049] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"ee4802602e11488bace331ddb2e836b4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_annotation.csv","filename":"sarscov2_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_peptidesequences.fasta","filename":"sarscov2_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_cleavedsequences.fasta","filename":"sarscov2_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_fullsequences.fasta","filename":"sarscov2_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_annotation.stat.csv","filename":"sarscov2_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_peptidesequences.stat.csv","filename":"sarscov2_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_cleavedsequences.stat.csv","filename":"sarscov2_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_signalp_fullsequences.stat.csv","filename":"sarscov2_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:42.243000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000444/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000444/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV2 Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T11:59:02.009860","modified":"2024-06-03T20:43:07.128Z","version":"v-0.0.0"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"7c7c97fcebe1e33f3c8ecaee76de6e7c68e61e0edd51518cdf783c1f1e1ca138","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":386,"last_update":"2024-06-03T20:43:07.128809Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000444/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000444/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T11:59:02.009860","modified":"2022-09-26T09:05:56.488840","version":"v-2.0.2"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"23ed1432968b686478705c37570648a9a1cb7935ef813d3feb02258d3b9a8f25","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.225000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000444/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000444/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T11:59:02.009860","modified":"2022-09-26T09:05:56.488840","version":"v-2.1.1"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"a1eb829508082d42e086529a22809023","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:42.427000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000446/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000446/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e2a76f751ae82930f558a575afd5204249633a47fa7f080105a3aae2c7ccf730","provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref ChEMBL","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T12:13:55.769499","modified":"2024-06-18T15:34:59.692Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref ChEMBL dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["bioactivity","ChEMBL","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_chembl.csv","filename":"sarscov1_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_chembl.stat.csv","filename":"sarscov1_protein_xref_chembl.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":433,"last_update":"2024-06-18T15:34:59.692588Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000446/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000446/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 UniProtKB Xref ChEMBL","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:13:55.769499","modified":"2022-09-26T09:05:56.522854","version":"v-2.0.2"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_chembl.csv","filename":"sarscov1_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref ChEMBL contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"d22f3903080ffa3b2010d8b9a21f7616b741c9619caed677e35de298ee6bb326","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_chembl.csv","filename":"sarscov1_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_chembl.stat.csv","filename":"sarscov1_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.138000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000446/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000446/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref ChEMBL","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T12:13:55.769499","modified":"2022-09-26T09:05:56.522854","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_chembl.csv","filename":"sarscov1_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref ChEMBL contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"etag":"0b39f8ae113ab841ab57702c4c4ae352","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_chembl.csv","filename":"sarscov1_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_chembl.stat.csv","filename":"sarscov1_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:42.612000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000447/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000447/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T12:15:30.637510","modified":"2025-08-01T17:03:31.684Z","version":"v-0.0.0"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref NCBI Gene dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"9f49df1f4218295967923c5a973a672d000b0534422e6a7fcd95510b9e4906a7","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_geneid.csv","filename":"sarscov1_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_geneid.stat.csv","filename":"sarscov1_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":691,"last_update":"2025-08-01T17:03:31.684691Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000447/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000447/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:15:30.637510","modified":"2022-09-26T09:05:56.498922","version":"v-2.0.2"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_geneid.csv","filename":"sarscov1_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref NCBI Gene dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"62eddfcd0328a75837fb1f5bfb7e6bb30c4c74b0199757bba35faa6960f93440","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_geneid.csv","filename":"sarscov1_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_geneid.stat.csv","filename":"sarscov1_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.118000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000447/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000447/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T12:15:30.637510","modified":"2022-09-26T09:05:56.498922","version":"v-2.1.1"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_geneid.csv","filename":"sarscov1_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref NCBI Gene dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"8c30a447e5e94aa41ce22b32f608c951","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_geneid.csv","filename":"sarscov1_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_geneid.stat.csv","filename":"sarscov1_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:42.800000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000448/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000448/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref IntAct","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T12:16:43.851012","modified":"2024-06-03T21:18:15.835Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref IntAct dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"354ecd4a794ad61634d69ec792ee2f44e7f4c92b08ad831f54bd30319afe68e6","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_intact.csv","filename":"sarscov1_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_intact.stat.csv","filename":"sarscov1_protein_xref_intact.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":594,"last_update":"2024-06-03T21:18:15.835454Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000448/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000448/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 UniProtKB Xref IntAct","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:16:43.851012","modified":"2022-09-26T09:05:56.481096","version":"v-2.0.2"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_intact.csv","filename":"sarscov1_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref IntAct dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"b1f1ad0c376bf05815105a3283d4cfc5d84b145953dda3346b1eb326eee55a0e","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_intact.csv","filename":"sarscov1_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_intact.stat.csv","filename":"sarscov1_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.131000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000448/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000448/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref IntAct","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T12:16:43.851012","modified":"2022-09-26T09:05:56.481096","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_intact.csv","filename":"sarscov1_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref IntAct dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"etag":"63f592d0047ad96b92aa14059415f458","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_intact.csv","filename":"sarscov1_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_intact.stat.csv","filename":"sarscov1_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:42.990000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000449/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000449/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"31f8374deebf28abbd9987410d8042c7331ae8d21f3a75e254c9d0a37b6e4a7b","provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref InterPro","version":"v-0.0.0","created":"2020-04-03T12:25:01.015736","modified":"2024-06-18T15:34:37.531Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref InterPro dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}],"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_interpro.csv","filename":"sarscov1_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_interpro.stat.csv","filename":"sarscov1_protein_xref_interpro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":539,"last_update":"2024-06-18T15:34:37.531804Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000449/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000449/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:25:01.015736","modified":"2022-09-26T09:05:56.465709","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_interpro.csv","filename":"sarscov1_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref InterPro contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"2ce5ed768afdd5c12dcc63846b90bd3e92ae5f3f223c780a7ee4b3073283d6b6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_interpro.csv","filename":"sarscov1_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_interpro.stat.csv","filename":"sarscov1_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.795000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000449/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000449/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T12:25:01.015736","modified":"2022-09-26T09:05:56.465709","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_interpro.csv","filename":"sarscov1_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref InterPro contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"5ed09552354b38f1dad5f33d1764c65a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_interpro.csv","filename":"sarscov1_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_interpro.stat.csv","filename":"sarscov1_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:43.183000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000450/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000450/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4bb5c70245266e338d9e00c362f3f90b5a48cfaca506fa4a29e690e4e7f3e387","provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref InterPro","version":"v-0.0.0","created":"2020-04-03T12:27:47.989476","modified":"2024-06-18T15:34:26.762Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref InterPro dataset contains Severe acute respiratory syndrome coronavirus 2  [taxid:2697049] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}],"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_interpro.csv","filename":"sarscov2_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_interpro.stat.csv","filename":"sarscov2_protein_xref_interpro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":548,"last_update":"2024-06-18T15:34:26.762461Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000450/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000450/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:27:47.989476","modified":"2022-09-26T09:05:56.520940","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_interpro.csv","filename":"sarscov2_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref InterPro contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"c0ef3d2ce9da3971ef7210a94cb2e9d4470da9fc70398fb181cc5ee03f5a5f44","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_interpro.csv","filename":"sarscov2_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_interpro.stat.csv","filename":"sarscov2_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.985000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000450/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000450/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref InterPro","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T12:27:47.989476","modified":"2022-09-26T09:05:56.520940","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_interpro.csv","filename":"sarscov2_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref InterPro contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"etag":"3afc3c51ac65b895f7ad1292f904a453","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_interpro.csv","filename":"sarscov2_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_interpro.stat.csv","filename":"sarscov2_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:43.369000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000451/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000451/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"aaebd33191345654a0e85955c2d583af2618b4bdb838281b837f7910f3bb499b","provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref PDB","version":"v-0.0.0","license":"MIT","created":"2020-04-03T12:28:56.594146","modified":"2024-06-18T15:34:06.662Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref PDB dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["protein 3D structure","RCSB PDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_pdb.csv","filename":"sarscov1_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_pdb.stat.csv","filename":"sarscov1_protein_xref_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":462,"last_update":"2024-06-18T15:34:06.661998Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000451/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000451/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:28:56.594146","modified":"2022-09-26T09:05:56.500236","version":"v-2.0.2"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_pdb.csv","filename":"sarscov1_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref PDB contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"7a55d23b32e582102bc735cc415c4f5a6d127a01da40d20adbf42acae3b9a882","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_pdb.csv","filename":"sarscov1_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_pdb.stat.csv","filename":"sarscov1_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.541000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000451/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000451/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref PDB","version":"v-2.1.1","license":"MIT","created":"2020-04-03T12:28:56.594146","modified":"2022-09-26T09:05:56.500236","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_pdb.csv","filename":"sarscov1_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref PDB contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"14e75a470dff7e42b0e15871721f5b41","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_pdb.csv","filename":"sarscov1_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_pdb.stat.csv","filename":"sarscov1_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:43.562000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000452/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000452/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2cc83b6556a2b200c03f1f0873c300d4bea6491a574bba5bb78551fb26a360c7","provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref PDB","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-03T12:29:53.528902","modified":"2024-06-18T15:33:50.182Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref PDB dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["protein 3D structure","RCSB PDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_pdb.csv","filename":"sarscov2_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_pdb.stat.csv","filename":"sarscov2_protein_xref_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":470,"last_update":"2024-06-18T15:33:50.182476Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000452/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000452/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:29:53.528902","modified":"2022-09-26T09:05:56.490280","version":"v-2.0.2"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_pdb.csv","filename":"sarscov2_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref PDB contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"57b7b0740ba2950180149d7da0559b50953718f539b5ca5cfa1c4b36f55e5306","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_pdb.csv","filename":"sarscov2_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_pdb.stat.csv","filename":"sarscov2_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.886000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000452/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000452/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 UniProtKB Xref PDB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T12:29:53.528902","modified":"2022-09-26T09:05:56.490280","version":"v-2.1.1"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_pdb.csv","filename":"sarscov2_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref PDB contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"etag":"4d55b8342006b1e0df5c34e75061ab46","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_pdb.csv","filename":"sarscov2_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_pdb.stat.csv","filename":"sarscov2_protein_xref_pdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:43.755000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000453/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000453/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1eb5d6065efb9e7262071d68463505ec88acb300a9781fbc949846b59d556efd","provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref Pfam","version":"v-0.0.0","license":"MIT","created":"2020-04-03T12:31:06.030781","modified":"2024-06-18T15:33:38.923Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref Pfam dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["protein family","Pfam","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_pfam.csv","filename":"sarscov1_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_pfam.stat.csv","filename":"sarscov1_protein_xref_pfam.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":461,"last_update":"2024-06-18T15:33:38.923360Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000453/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000453/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:31:06.030781","modified":"2022-09-26T09:05:56.454209","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_pfam.csv","filename":"sarscov1_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref Pfam contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"078280665804ba1d39a8270a6163202fd55ed8cc1151c2467af9d4a2f9d0b28d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_pfam.csv","filename":"sarscov1_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_pfam.stat.csv","filename":"sarscov1_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.303000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000453/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000453/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref Pfam","version":"v-2.1.1","license":"MIT","created":"2020-04-03T12:31:06.030781","modified":"2022-09-26T09:05:56.454209","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_pfam.csv","filename":"sarscov1_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref Pfam contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"d61cc0995cdb7545db8dc32a37d0130d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_pfam.csv","filename":"sarscov1_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_pfam.stat.csv","filename":"sarscov1_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:43.962000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000454/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000454/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7046f6103c38525b40ed2e5e1729591185fa423a7a57eaa4eb0f56cfcca7ad38","provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref Pfam","version":"v-0.0.0","created":"2020-04-03T12:33:52.055648","modified":"2024-06-18T15:33:19.627Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref Pfam dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["protein family","Pfam","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_pfam.csv","filename":"sarscov2_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_pfam.stat.csv","filename":"sarscov2_protein_xref_pfam.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":469,"last_update":"2024-06-18T15:33:19.627098Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000454/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000454/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:33:52.055648","modified":"2022-09-26T09:05:56.442967","version":"v-2.0.2"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_pfam.csv","filename":"sarscov2_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref Pfam contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"08ea97ad7b43103ac3d6b904118ef3852cbd6a618e98ed0991064a2dcc2dda09","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_pfam.csv","filename":"sarscov2_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_pfam.stat.csv","filename":"sarscov2_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.742000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000454/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000454/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref Pfam","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T12:33:52.055648","modified":"2022-09-26T09:05:56.442967","version":"v-2.1.1"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_pfam.csv","filename":"sarscov2_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref Pfam contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"etag":"a80b10b238215b184d66670d24daae33","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_pfam.csv","filename":"sarscov2_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_pfam.stat.csv","filename":"sarscov2_protein_xref_pfam.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:44.143000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000455/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000455/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b7e0b19a3d40d6f4c6007e993a5d8607f460c0d1989f2f9fd2e7c65ce7c92f37","provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref RefSeq","version":"v-0.0.0","license":"MIT","created":"2020-04-03T12:35:06.443973","modified":"2024-06-18T15:32:38.508Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref RefSeq dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["protein accessions","RefSeq","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_refseq.stat.csv","filename":"sarscov1_protein_xref_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":709,"last_update":"2024-06-18T15:32:38.508350Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000455/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000455/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref RefSeq","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T12:35:06.443973","modified":"2022-09-26T09:05:56.424503","version":"v-2.0.2"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref RefSeq contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2020-01 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"etag":"1560a29d73e1d430d6a53185dbf42611438c41c016ce25df073a9a6162ed431f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.stat.csv","filename":"sarscov1_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.778000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000455/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000455/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref RefSeq","version":"v-2.1.1","license":"MIT","created":"2020-04-03T12:35:06.443973","modified":"2022-09-26T09:05:56.424503","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref RefSeq contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2020-01 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"etag":"0b1614ccf1fdf6a838df45866e7db273","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.stat.csv","filename":"sarscov1_protein_xref_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:44.333000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000456/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000456/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c02b81986eb5845a969a40a1024f1af48b5f8ce1179acbad44455e3b0f4d61fc","provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref RefSeq","version":"v-0.0.0","created":"2020-04-03T12:35:54.612692","modified":"2024-06-18T15:32:10.694Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniprotKB Xref RefSeq dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["protein accessions","RefSeq","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_refseq.stat.csv","filename":"sarscov2_protein_xref_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":717,"last_update":"2024-06-18T15:32:10.694082Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000456/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.stat.csv","filename":"sarscov2_protein_xref_refseq.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"","created":"2020-04-03T12:35:54.612692","modified":"2022-09-26T09:05:56.550905","version":"v-2.0.2","name":"SARS-CoV2 UniProtKB Xref RefSeq"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniprotKB Xref RefSeq contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2020-01 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"object_id":"https://biocomputeobject.org/GLY_000456/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5392beee99244f9c37c8b8455900e194c58b4e0c667fcf1d8c478ea21c319693"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.855000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000456/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.stat.csv","filename":"sarscov2_protein_xref_refseq.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"","created":"2020-04-03T12:35:54.612692","modified":"2022-09-26T09:05:56.550905","version":"v-2.1.1","name":"SARS-CoV2 UniProtKB Xref RefSeq"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniprotKB Xref RefSeq contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2020-01 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"object_id":"https://biocomputeobject.org/GLY_000456/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"89efa99f2de87e1a0aa8b24069de699a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:44.515000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000457/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000457/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T15:52:11.121013","modified":"2024-05-17T11:24:01.238Z","version":"v-0.0.0"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Signal Peptide dataset contains Mus musculus [taxid:10090] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"a9e1e9df788924c38a7ef1bfe758803a64483b6557caffb772cac5344bafb9ac","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_annotation.csv","filename":"mouse_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_peptidesequences.fasta","filename":"mouse_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_cleavedsequences.fasta","filename":"mouse_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_fullsequences.fasta","filename":"mouse_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_annotation.stat.csv","filename":"mouse_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_peptidesequences.stat.csv","filename":"mouse_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_cleavedsequences.stat.csv","filename":"mouse_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_signalp_fullsequences.stat.csv","filename":"mouse_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":614,"last_update":"2024-05-17T11:24:01.238740Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000457/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000457/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T15:52:11.121013","modified":"2022-09-26T09:05:56.547346","version":"v-2.0.2"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_signalp_annotation.csv","filename":"mouse_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_signalp_peptidesequences.fasta","filename":"mouse_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_signalp_cleavedsequences.fasta","filename":"mouse_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_signalp_fullsequences.fasta","filename":"mouse_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Signal Peptide dataset contains mouse [taxid:10090] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"219f47e4a874d262227879b080b2573a98b3387638a672e9b716db7210d08daa","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_annotation.csv","filename":"mouse_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_peptidesequences.fasta","filename":"mouse_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_cleavedsequences.fasta","filename":"mouse_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_fullsequences.fasta","filename":"mouse_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_annotation.stat.csv","filename":"mouse_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_peptidesequences.stat.csv","filename":"mouse_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_cleavedsequences.stat.csv","filename":"mouse_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_signalp_fullsequences.stat.csv","filename":"mouse_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.314000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000457/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000457/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T15:52:11.121013","modified":"2022-09-26T09:05:56.547346","version":"v-2.1.1"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_signalp_annotation.csv","filename":"mouse_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_signalp_peptidesequences.fasta","filename":"mouse_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_signalp_cleavedsequences.fasta","filename":"mouse_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_signalp_fullsequences.fasta","filename":"mouse_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Mouse Protein Signal Peptide dataset contains mouse [taxid:10090] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"ffeb520bd8bdb261a849c3d95ed80e13","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_annotation.csv","filename":"mouse_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_peptidesequences.fasta","filename":"mouse_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_cleavedsequences.fasta","filename":"mouse_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_fullsequences.fasta","filename":"mouse_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_annotation.stat.csv","filename":"mouse_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_peptidesequences.stat.csv","filename":"mouse_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_cleavedsequences.stat.csv","filename":"mouse_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_signalp_fullsequences.stat.csv","filename":"mouse_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:44.706000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000458/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000458/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T15:52:36.427462","modified":"2024-05-17T11:24:01.278Z","version":"v-0.0.0"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Signal Peptide dataset contains Rattus norvegicus [taxid:10116] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"0824a81b3f55903a77b1e20b93ae594aad527c574ea2bc5ac8b3b517b847e4f5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_annotation.csv","filename":"rat_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_peptidesequences.fasta","filename":"rat_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_cleavedsequences.fasta","filename":"rat_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_fullsequences.fasta","filename":"rat_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_annotation.stat.csv","filename":"rat_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_peptidesequences.stat.csv","filename":"rat_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_cleavedsequences.stat.csv","filename":"rat_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_signalp_fullsequences.stat.csv","filename":"rat_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":616,"last_update":"2024-05-17T11:24:01.278241Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000458/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000458/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T15:52:36.427462","modified":"2022-09-26T09:05:56.450738","version":"v-2.0.2"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_signalp_annotation.csv","filename":"rat_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_signalp_peptidesequences.fasta","filename":"rat_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_signalp_cleavedsequences.fasta","filename":"rat_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_signalp_fullsequences.fasta","filename":"rat_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Signal Peptide dataset contains rat [taxid:10116] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"47f9adfba982aff3d4463a858f856a924b1afd7f3e6fb49368a5b1ee92732bc0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_annotation.csv","filename":"rat_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_peptidesequences.fasta","filename":"rat_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_cleavedsequences.fasta","filename":"rat_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_fullsequences.fasta","filename":"rat_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_annotation.stat.csv","filename":"rat_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_peptidesequences.stat.csv","filename":"rat_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_cleavedsequences.stat.csv","filename":"rat_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_signalp_fullsequences.stat.csv","filename":"rat_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.216000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000458/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000458/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Signal Peptide","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T15:52:36.427462","modified":"2022-09-26T09:05:56.450738","version":"v-2.1.1"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_signalp_annotation.csv","filename":"rat_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_signalp_peptidesequences.fasta","filename":"rat_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_signalp_cleavedsequences.fasta","filename":"rat_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_signalp_fullsequences.fasta","filename":"rat_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Protein Signal Peptide dataset contains rat [taxid:10116] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"e6af6463367577e2be2d5c3a7e91b727","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_annotation.csv","filename":"rat_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_peptidesequences.fasta","filename":"rat_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_cleavedsequences.fasta","filename":"rat_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_fullsequences.fasta","filename":"rat_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_annotation.stat.csv","filename":"rat_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_peptidesequences.stat.csv","filename":"rat_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_cleavedsequences.stat.csv","filename":"rat_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_signalp_fullsequences.stat.csv","filename":"rat_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:44.899000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000459/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000459/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Human Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T17:17:42.572968","modified":"2024-06-03T20:59:01.975Z","version":"v-0.0.0"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human Germline Mutation dataset contains Homo sapiens [taxid:9606] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"d63a71e185c160daf898f6418375444b834d7cb2a064100d70b4db0229493129","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_germline.csv","filename":"human_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_germline.stat.csv","filename":"human_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":297,"last_update":"2024-06-03T20:59:01.975236Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000459/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000459/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T17:17:42.572968","modified":"2022-09-26T09:05:56.408743","version":"v-2.0.2"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}],"prerequisite":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Germline Mutation dataset contains human [taxid:9606] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"05115df15fd688229ac1d8b9fd1c025a1aa33e3c16d78e566287daeeeccaaee1","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-homo-sapiens.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/dbSNP-homo-sapiens.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_germline.csv","filename":"human_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_germline.stat.csv","filename":"human_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.879000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000459/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000459/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T17:17:42.572968","modified":"2022-09-26T09:05:56.408743","version":"v-2.1.1"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}],"prerequisite":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Germline Mutation dataset contains human [taxid:9606] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"06b8c9503c68a2f7a5859b266b668ce2","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-homo-sapiens.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/dbSNP-homo-sapiens.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_germline.csv","filename":"human_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_germline.stat.csv","filename":"human_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:45.094000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000460/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000460/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Mouse Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T17:22:53.520266","modified":"2024-06-03T20:59:24.013Z","version":"v-0.0.0"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Germline Mutation dataset contains Mus musculus [taxid:10090] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"0b696d37f2d53fdd54216b53e8f58d3def6b2e24f37b7fc48acd3b42793be3ee","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_mutation_germline.csv","filename":"mouse_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_mutation_germline.stat.csv","filename":"mouse_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":298,"last_update":"2024-06-03T20:59:24.013205Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000460/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000460/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T17:22:53.520266","modified":"2022-09-26T09:05:56.557625","version":"v-2.0.2"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/dbSNP-mus-musculus.tsv","filename":"dbSNP-mus-musculus.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_mutation_germline.csv","filename":"mouse_protein_mutation_germline.csv"}],"prerequisite":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Germline Mutation dataset contains mouse [taxid:10090] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"64a56651aadd61a93504521193fadc895b27ce41cee64b6f7e0eb8776d31ba12","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-mus-musculus.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/dbSNP-mus-musculus.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_mutation_germline.csv","filename":"mouse_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_mutation_germline.stat.csv","filename":"mouse_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.658000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000460/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000460/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T17:22:53.520266","modified":"2022-09-26T09:05:56.557625","version":"v-2.1.1"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/dbSNP-mus-musculus.tsv","filename":"dbSNP-mus-musculus.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_mutation_germline.csv","filename":"mouse_protein_mutation_germline.csv"}],"prerequisite":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Germline Mutation dataset contains mouse [taxid:10090] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"b114622890fae30c840601213be44b1e","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-mus-musculus.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/dbSNP-mus-musculus.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_mutation_germline.csv","filename":"mouse_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_mutation_germline.stat.csv","filename":"mouse_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:45.289000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000461/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000461/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Rat Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T17:25:56.930719","modified":"2024-06-03T20:59:40.433Z","version":"v-0.0.0"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the germline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Rat Germline Mutation dataset contains Rattus norvegicus [taxid:10116] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB. "],"etag":"413a8fe7e4a0bc8bc5cfe59433f1ea8a3eb265204f191046c921d4fb693e2880","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_mutation_germline.csv","filename":"rat_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_mutation_germline.stat.csv","filename":"rat_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":302,"last_update":"2024-06-03T20:59:40.433015Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000461/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000461/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T17:25:56.930719","modified":"2022-09-26T09:05:56.535607","version":"v-2.0.2"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/dbSNP-rattus-norvegicus.tsv","filename":"dbSNP-rattus-norvegicus.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_mutation_cancer.csv","filename":"rat_protein_mutation_germline.csv"}],"prerequisite":[],"description":"The script extracts the germline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Germline Mutation dataset contains rat [taxid:10116] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB. "],"etag":"4bfa921d9458c51e29666b240bb7bf754438064a6de9759d5a492ecd48ffe84f","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-rattus-norvegicus.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/dbSNP-rattus-norvegicus.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_mutation_germline.csv","filename":"rat_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_mutation_germline.stat.csv","filename":"rat_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.221000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000461/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000461/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Germline Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T17:25:56.930719","modified":"2022-09-26T09:05:56.535607","version":"v-2.1.1"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/dbSNP-rattus-norvegicus.tsv","filename":"dbSNP-rattus-norvegicus.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_mutation_cancer.csv","filename":"rat_protein_mutation_germline.csv"}],"prerequisite":[],"description":"The script extracts the germline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Germline Mutation dataset contains rat [taxid:10116] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB. "],"etag":"9b31a1bb7543281ea5c72983ee208a7a","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-rattus-norvegicus.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/dbSNP-rattus-norvegicus.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_mutation_germline.csv","filename":"rat_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_mutation_germline.stat.csv","filename":"rat_protein_mutation_germline.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:45.478000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000462/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000462/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Human Somatic Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T17:17:42.572968","modified":"2024-06-03T20:59:59.368Z","version":"v-0.0.0"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","somatic mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the somatic (somatic_staus = 1) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human Somatic Mutation dataset contains Homo sapiens [taxid:9606] somatic mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) somatic mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"2ffaf6195532ed38e14853aa4de6670780e6b50b165a14d518364a408c2adbb4","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_somatic.csv","filename":"human_protein_mutation_somatic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_somatic.stat.csv","filename":"human_protein_mutation_somatic.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":294,"last_update":"2024-06-03T20:59:59.368656Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000462/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000462/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Somatic Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T17:17:42.572968","modified":"2022-09-26T09:05:56.448058","version":"v-2.0.2"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","somatic mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_mutation_somatic.csv","filename":"human_protein_mutation_somatic.csv"}],"prerequisite":[],"description":"The script extracts the somatic (somatic_staus = 1) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Somatic Mutation dataset contains human [taxid:9606] somatic mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) somatic mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"dd94a7795f432bce0432ce60e10184093c73c9fe39f7dd597ba3642bbf0fa9aa","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-homo-sapiens.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/dbSNP-homo-sapiens.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_somatic.csv","filename":"human_protein_mutation_somatic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_somatic.stat.csv","filename":"human_protein_mutation_somatic.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.726000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000462/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000462/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Somatic Mutation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T17:17:42.572968","modified":"2022-09-26T09:05:56.448058","version":"v-2.1.1"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","somatic mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_mutation_somatic.csv","filename":"human_protein_mutation_somatic.csv"}],"prerequisite":[],"description":"The script extracts the somatic (somatic_staus = 1) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Somatic Mutation dataset contains human [taxid:9606] somatic mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) somatic mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"etag":"443dd10477485189d9cf4d4fc4031500","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}},{"uri":{"filename":"dbSNP-homo-sapiens.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/dbSNP-homo-sapiens.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_somatic.csv","filename":"human_protein_mutation_somatic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_somatic.stat.csv","filename":"human_protein_mutation_somatic.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:45.666000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000463/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000463/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Literature Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Literature Mutations","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T17:37:22.702254","modified":"2024-05-17T11:24:01.470Z","version":"v-0.0.0"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","literature mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the mutation data only for the mutations that have amino acid information and position from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Literature Mutation dataset contains human [taxid:9606] mutation data extracted from literature using the DIMEX tool. The dataset contains only the mutations that have amino acid information and position in the mutation mention column.. If you use this dataset provide proper attribution to GlyGen and OncoMX."],"etag":"6b138af025a7a98c9d09cd97a3c0701dc7fd202bbc7dbb40f2bdda3ad014a44d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_literature.csv","filename":"human_protein_mutation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_literature.stat.csv","filename":"human_protein_mutation_literature.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":319,"last_update":"2024-05-17T11:24:01.470767Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000463/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000463/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Literature Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Literature Mutations","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-03T17:37:22.702254","modified":"2022-09-26T09:05:56.414270","version":"v-2.0.2"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","literature mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_literature.csv"}],"prerequisite":[],"description":"The script extracts the mutation data only for the mutations that have amino acid information and position from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Literature Mutation dataset contains human [taxid:9606] mutation data extracted from literature using the DIMEX tool. The dataset contains only the mutations that have amino acid information and position in the mutation mention column.. If you use this dataset provide proper attribution to GlyGen and OncoMX."],"etag":"ef343b6acb471873fff5324e45dac9d5886872c2eff2fba0795b96ce591b08ae","io_domain":{"input_subdomain":[{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}},{"uri":{"filename":"human_cancer_mutation_literature.csv","uri":"https:/data.glygen.org/ln2downloads/biomuta/v-3.0/human_cancer_mutation_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_literature.csv","filename":"human_protein_mutation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_literature.stat.csv","filename":"human_protein_mutation_literature.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.707000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000463/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000463/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Literature Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Literature Mutations","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T17:37:22.702254","modified":"2022-09-26T09:05:56.414270","version":"v-2.1.1"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","literature mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_literature.csv"}],"prerequisite":[],"description":"The script extracts the mutation data only for the mutations that have amino acid information and position from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Literature Mutation dataset contains human [taxid:9606] mutation data extracted from literature using the DIMEX tool. The dataset contains only the mutations that have amino acid information and position in the mutation mention column.. If you use this dataset provide proper attribution to GlyGen and OncoMX."],"etag":"e1d0ee5c1356fd22a9a3ceecaac347b3","io_domain":{"input_subdomain":[{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}},{"uri":{"filename":"human_cancer_mutation_literature.csv","uri":"/data/shared/glyds/downloads/biomuta/v-5.0/human_cancer_mutation_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_literature.csv","filename":"human_protein_mutation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_literature.stat.csv","filename":"human_protein_mutation_literature.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:45.853000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000464/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000464/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-Pharos Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"GlyGen-Pharos Crossreferences Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-03T22:31:02.233246","modified":"2024-05-17T11:24:01.507Z","version":"v-0.0.0"},"description_domain":{"keywords":["Pharos","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the human UniProtKB GlyGen accessions that mapped to the Pharos protein accessions along with the GlyGen protein accession URL and extracts it into csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The GlyGen-Pharos Cross-references Mapping dataset contains GlyGen's Homo sapiens [taxid:9606] UniProtKB accessions and corresponding GlyGen URLs.","The dataset is created for Pharos database to crosslink their protein page links to GlyGen protein pages.","The log file contains the Pharos protein accessions that could not be mapped to GlyGen protein accessions."],"etag":"7ef329401e477984eaa95cc1a978a4d72d50d1dc2cda65442d927975edc7582e","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_pharos_xref_mapping.csv","filename":"protein_glygen_pharos_xref_mapping.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_pharos_xref_mapping.stat.csv","filename":"protein_glygen_pharos_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-17T11:24:01.507005Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000464/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000464/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-Pharos Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"GlyGen-Pharos Crossreferences Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-04-03T22:31:02.233246","modified":"2022-09-26T09:05:56.479326","version":"v-2.0.2"},"description_domain":{"keywords":["Pharos","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_protein_xref_pharos.csv","filename":"human_protein_xref_pharos.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/protein_glygen_pharos_xref_mapping.csv","filename":"protein_glygen_pharos_xref_mapping.csv"}],"prerequisite":[],"description":"The script loads the human UniProtKB GlyGen accessions that mapped to the Pharos protein accessions along with the GlyGen protein accession URL and extracts it into csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The GlyGen-Pharos Cross-references Mapping dataset contains GlyGen's human [taxid:9606] UniProtKB accessions and corresponding GlyGen URLs. The dataset is derived from 2019-09 UniProtKB release.","The dataset is created for Pharos database to crosslink their protein page links to GlyGen protein pages.","The log file contains the Pharos protein accessions that could not be mapped to GlyGen protein accessions"],"etag":"c15362c84a913b04cb8aa7c7b0c71ef6430f7ab173584031339db0d3e7d8373f","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_pharos_xref_mapping.csv","filename":"protein_glygen_pharos_xref_mapping.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_pharos_xref_mapping.stat.csv","filename":"protein_glygen_pharos_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.683000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000464/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000464/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-Pharos Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"provenance_domain":{"license":"","name":"GlyGen-Pharos Crossreferences Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-03T22:31:02.233246","modified":"2022-09-26T09:05:56.479326","version":"v-2.1.1"},"description_domain":{"keywords":["Pharos","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_protein_xref_pharos.csv","filename":"human_protein_xref_pharos.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/protein_glygen_pharos_xref_mapping.csv","filename":"protein_glygen_pharos_xref_mapping.csv"}],"prerequisite":[],"description":"The script loads the human UniProtKB GlyGen accessions that mapped to the Pharos protein accessions along with the GlyGen protein accession URL and extracts it into csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The GlyGen-Pharos Cross-references Mapping dataset contains GlyGen's human [taxid:9606] UniProtKB accessions and corresponding GlyGen URLs. The dataset is derived from 2019-09 UniProtKB release.","The dataset is created for Pharos database to crosslink their protein page links to GlyGen protein pages.","The log file contains the Pharos protein accessions that could not be mapped to GlyGen protein accessions"],"etag":"8f54d0c8b4026089a74ae36435e63765","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_pharos_xref_mapping.csv","filename":"protein_glygen_pharos_xref_mapping.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_pharos_xref_mapping.stat.csv","filename":"protein_glygen_pharos_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:46.046000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000465/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000465/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Site Annotation","version":"v-0.0.0","license":"MIT","created":"2020-04-09T13:22:15.821413","modified":"2024-06-03T20:43:40.666Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"316cbbadb02cea91997d8afaec96428277f3d503793002231c3fd58f8c50ad7a","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":378,"last_update":"2024-06-03T20:43:40.666858Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000465/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000465/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-09T13:22:15.821413","modified":"2022-09-26T09:05:56.467926","version":"v-2.0.2"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"678387b8dcd5d1bf70ab7e2f68db071ea514ab9bc2d26dda1f64256929488c2d","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.021000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000465/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000465/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Protein Site Annotation","version":"v-2.1.1","license":"MIT","created":"2020-04-09T13:22:15.821413","modified":"2022-09-26T09:05:56.467926","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"etag":"035c7204f9f2e193c3c753b572cbca60","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:46.238000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000466/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000466/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-09T13:34:52.248699","modified":"2024-05-17T11:24:01.583Z","version":"v-0.0.0"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Information dataset contains hcv1b,Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"5a3f8929b51abd7bbb1a6a9028328eda632b817c866c308bc6b72e2ecc5cb486","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_info_uniprotkb.csv","filename":"hcv1b_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_info_uniprotkb.stat.csv","filename":"hcv1b_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2024-05-17T11:24:01.583864Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000466/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000466/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-09T13:34:52.248699","modified":"2022-09-26T09:05:56.513585","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_info_uniprotkb.csv","filename":"hcv1b_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Information dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"3fcde49297c7eb5d1ffb4fae5fdf255da041f78adf9645525e56a74f2cbe4350","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_info_uniprotkb.csv","filename":"hcv1b_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_info_uniprotkb.stat.csv","filename":"hcv1b_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.720000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000466/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000466/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Information (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-09T13:34:52.248699","modified":"2022-09-26T09:05:56.513585","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_info_uniprotkb.csv","filename":"hcv1b_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Information dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"128b572c4665999fc8bc577c6a38b5c9","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_info_uniprotkb.csv","filename":"hcv1b_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_info_uniprotkb.stat.csv","filename":"hcv1b_protein_info_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:46.425000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000467/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000467/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS CoV1 Proteome Masterlist (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-09T15:41:15.215497","modified":"2024-06-03T21:21:14.559Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Proteome Master list dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"f18430245bc29e1ff7158372b06b78a6d1622cb33cb856ad454de49b30c8622f","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_masterlist.stat.csv","filename":"sarscov1_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-06-03T21:21:14.559240Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000467/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000467/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS CoV1 Proteome Masterlist (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-09T15:41:15.215497","modified":"2022-09-26T09:05:56.509905","version":"v-2.0.2"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Proteome Master list dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"f4beefc448d6a97675d1adce4fab6023b7759cc2edc14a2ebca5143e9e60ea0f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.stat.csv","filename":"sarscov1_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.181000Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000467/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000467/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS CoV1 Proteome Masterlist (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-09T15:41:15.215497","modified":"2022-09-26T09:05:56.509905","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Proteome Master list dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"48a8a7761e7450a56cb1009a869e2459","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.stat.csv","filename":"sarscov1_protein_masterlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:46.617000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000468/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000468/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"HCV1a Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-09T15:57:45.462784","modified":"2024-05-17T11:24:01.660Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Function (UniProtKB) dataset contains biological function annotation for Hepatitis C virus (isolate H77) [taxid:63746] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"baa61f68eaa1c828b3f49098e472bb526626ecae94fa5a76ded2559a8fa3a230","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_function_uniprotkb.csv","filename":"hcv1a_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_function_uniprotkb.stat.csv","filename":"hcv1a_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":276,"last_update":"2024-05-17T11:24:01.660117Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000468/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000468/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1a Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-09T15:57:45.462784","modified":"2022-09-26T09:05:56.485564","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_function_uniprotkb.csv","filename":"hcv1a_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Function (UniProtKB) dataset contains biological function annotation for hcv1a [taxid:11108] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"e93decd9dabb466c206379fd20dfb1ddf6f4d3adf9a302b1dd2eaa7b14085321","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_function_uniprotkb.csv","filename":"hcv1a_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_function_uniprotkb.stat.csv","filename":"hcv1a_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.565000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000468/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000468/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1a Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-09T15:57:45.462784","modified":"2022-09-26T09:05:56.485564","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_function_uniprotkb.csv","filename":"hcv1a_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Function (UniProtKB) dataset contains biological function annotation for hcv1a [taxid:11108] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"bb1c74701c7379565e9412eb56992481","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_function_uniprotkb.csv","filename":"hcv1a_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_function_uniprotkb.stat.csv","filename":"hcv1a_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:46.809000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000469/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000469/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-09T16:00:53.329942","modified":"2024-05-17T11:24:01.699Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Function (UniProtKB) dataset contains biological function annotation for hcv1b,Hepatitis C virus (isolate Japanese) [taxid:11116] protein accesions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"cf757da930f799602ec22049fb14530a4f0949492f31e4c7ee486967adb8a4b2","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_function_uniprotkb.csv","filename":"hcv1b_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_function_uniprotkb.stat.csv","filename":"hcv1b_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":330,"last_update":"2024-05-17T11:24:01.699507Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000469/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000469/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-09T16:00:53.329942","modified":"2022-09-26T09:05:56.458077","version":"v-2.0.2"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_function_uniprotkb.csv","filename":"hcv1b_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Function (UniProtKB) dataset contains biological function annotation for hcv1b [taxid:11116] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"79c26e83db3f349a1a926e9227dbdd28f8daf94ae4f372ec7cf2d837c723cd89","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_function_uniprotkb.csv","filename":"hcv1b_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_function_uniprotkb.stat.csv","filename":"hcv1b_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.440000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000469/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000469/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Function (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-09T16:00:53.329942","modified":"2022-09-26T09:05:56.458077","version":"v-2.1.1"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_function_uniprotkb.csv","filename":"hcv1b_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Function (UniProtKB) dataset contains biological function annotation for hcv1b [taxid:11116] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"340ffc263f2aa22e432293e7d2cd0173","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_function_uniprotkb.csv","filename":"hcv1b_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_function_uniprotkb.stat.csv","filename":"hcv1b_protein_function_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:47.006000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000470/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000470/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV2 Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-19T11:32:35.963024","modified":"2024-06-03T21:21:42.530Z","version":"v-0.0.0"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Citations dataset contains publication information for Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB accessions that includes PMID, journal name, date and author and title. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"d9ee82d75529fc4b9d0474f0da94118681d667c22994190fb0781d71284695c1","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_citations_uniprotkb.stat.csv","filename":"sarscov2_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":347,"last_update":"2024-06-03T21:21:42.530818Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000470/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000470/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-19T11:32:35.963024","modified":"2022-09-26T09:05:56.517431","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Citations dataset contains publication information for sarscov2 [taxid:2697049] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"60bf2405faf2e82fe5d831b2f54d26d6898ed104a05e347193b47ab36326a866","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_citations_uniprotkb.stat.csv","filename":"sarscov2_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.943000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000470/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000470/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-19T11:32:35.963024","modified":"2022-09-26T09:05:56.517431","version":"v-2.1.1"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Citations dataset contains publication information for sarscov2 [taxid:2697049] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"dfa790e9613a08e90bd7d5d44ace4de8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_citations_uniprotkb.stat.csv","filename":"sarscov2_protein_citations_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:47.198000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000471/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000471/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9980d1501ef4dca522fcd2f5e8b40edf1f2f76066a1221d91c5bb14d8557fd36","provenance_domain":{"name":"SARS-CoV1 Protein PTM Annotation (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-19T11:41:41.632491","modified":"2024-12-10T19:34:07.117Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein PTM Annotation (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}],"keywords":["ptm annotation","glycosylation","phosphorylation"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":525,"last_update":"2024-12-10T19:34:07.117882Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000471/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000471/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-19T11:41:41.632491","modified":"2022-09-26T09:05:56.502631","version":"v-2.0.2"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein PTM Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"2051ae1e3a5b8057cc0d2df08d4808a763b04732b06dd81a5385d8636e0dde77","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.339000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000471/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000471/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-19T11:41:41.632491","modified":"2022-09-26T09:05:56.502631","version":"v-2.1.1"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein PTM Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"3fefb56f647d59857b6d176f6654c150","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:47.390000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000472/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000472/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-19T11:44:49.318101","modified":"2024-05-17T11:24:01.820Z","version":"v-0.0.0"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein PTM Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"6b0c14c3edd81444245834991440771f4fc7043c18c819f0d133299524fc8463","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":403,"last_update":"2024-05-17T11:24:01.820431Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000472/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000472/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-19T11:44:49.318101","modified":"2022-09-26T09:05:56.474034","version":"v-2.0.2"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein PTM Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"a6b7ab7339c0961cca9742386bea86046978ed34a641394556787aa2bbe6c874","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.625000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000472/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000472/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein PTM Annotation (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-19T11:44:49.318101","modified":"2022-09-26T09:05:56.474034","version":"v-2.1.1"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein PTM Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"a320cd8aa4a084cbf905715aa480b745","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:47.576000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000473/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000473/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-19T12:02:17.236691","modified":"2024-06-03T21:22:00.021Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Glycosylation Sites (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"c386eb889c673a7daa171fedd0b1223bbe9fc05b39d603ac2fa21d45474004ce","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":369,"last_update":"2024-06-03T21:22:00.021499Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000473/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000473/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-19T12:02:17.236691","modified":"2022-09-26T09:05:56.471980","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Glycosylation Sites (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"2b4285982e00a3f4adf105904f6c20df8f4bf935ebc6924dafe045738aec9e52","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.780000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000473/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000473/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-19T12:02:17.236691","modified":"2022-09-26T09:05:56.471980","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Glycosylation Sites (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"68266ee099d0bee91fa389601041ff20","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:47.757000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000474/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000474/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Phosphorylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-19T12:08:33.749000","modified":"2024-06-03T21:22:23.574Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Phosphorylation Sites (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"c6d97fe304926315c7e2be9fad0888f7d1d8d6cc520ba8935eecf284d1d4ff3a","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":379,"last_update":"2024-06-03T21:22:23.574432Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000474/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000474/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-19T12:08:33.749000","modified":"2022-09-26T09:05:56.445575","version":"v-2.0.2"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Phosphorylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"a9a22a15f62c4a98d09d774af2a422524a3a8660e4d137ec87d245cd1e0a13d3","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.609000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000474/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000474/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Phosphorylation Sites (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-19T12:08:33.749000","modified":"2022-09-26T09:05:56.445575","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Phosphorylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"2d3740d01882cfc6d774fffb07b1be95","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:47.946000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000475/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000475/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV2 Phosphorylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-19T12:18:14.955878","modified":"2024-06-03T21:22:42.111Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Phosphorylation Sites (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"94da0103a9199c60f709bd2b2f1d80ecb1cf6c046d77c62c21803c00dc04b94f","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":387,"last_update":"2024-06-03T21:22:42.111136Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000475/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000475/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Phosphorylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-19T12:18:14.955878","modified":"2022-09-26T09:05:56.420499","version":"v-2.0.2"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Phosphorylation Sites (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"d1939633953b651d4845b112f4b1297a3d9f752864127936467767a606a44774","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.931000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000475/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000475/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV2 Phosphorylation Sites (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-19T12:18:14.955878","modified":"2022-09-26T09:05:56.420499","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Phosphorylation Sites (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted phosphorylation sites with evidence in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"e37289f8b6cb1e632a12125da5f5c01f","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:48.137000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000476/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000476/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"rdf","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"rdf","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan data (RDF)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-20T14:23:42.722024","modified":"2024-05-17T11:24:01.977Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","rdf"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the provider and was provided to GlyGen users. (no additional processing is done)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides rdf fomat file for the glycan data. "],"etag":"2729ea64486f95e29f7b5f46f41035ed4893b2a9b19127e8f9fb407647e1c017","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"rdf","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_rdfdata.rdf.gz","filename":"glycan_rdfdata.rdf.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_rdfdata.rdf.stat.csv","filename":"glycan_rdfdata.rdf.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":57,"last_update":"2024-05-17T11:24:01.977890Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000476/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000476/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"rdf","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"rdf","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan data (RDF)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-20T14:23:42.722024","modified":"2022-09-26T09:05:56.567083","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","rdf"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycandata.rdf.gz","filename":"glycandata.rdf.gz"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_rdfdata.rdf.gz","filename":"glycan_rdfdata.rdf.gz"}],"prerequisite":[],"description":"The input file was downloaded from the provider and was provided to GlyGen users. (no additional processing is done)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides rdf fomat file for the glycan data. "],"etag":"e4efb6ac743f8d3788598c5321bcb5d0aedcced02037d829038bade5dc3df53c","io_domain":{"input_subdomain":[{"uri":{"filename":"glycandata.rdf.gz","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/glycandata.rdf.gz"}}],"output_subdomain":[{"mediatype":"rdf","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_rdfdata.rdf.gz","filename":"glycan_rdfdata.rdf.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_rdfdata.rdf.stat.csv","filename":"glycan_rdfdata.rdf.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.825000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000476/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000476/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"rdf","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"rdf","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan data (RDF)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-20T14:23:42.722024","modified":"2022-09-26T09:05:56.567083","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","rdf"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycandata.rdf.gz","filename":"glycandata.rdf.gz"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_rdfdata.rdf.gz","filename":"glycan_rdfdata.rdf.gz"}],"prerequisite":[],"description":"The input file was downloaded from the provider and was provided to GlyGen users. (no additional processing is done)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides rdf fomat file for the glycan data. "],"etag":"79de83433774c6441d7b5f8fe497e64d","io_domain":{"input_subdomain":[{"uri":{"filename":"glycandata.rdf.gz.00","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/glycandata.rdf.gz.00"}}],"output_subdomain":[{"mediatype":"rdf","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_rdfdata.rdf.gz","filename":"glycan_rdfdata.rdf.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_rdfdata.rdf.stat.csv","filename":"glycan_rdfdata.rdf.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:48.324000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000477/DRAFT","contents":{"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_image_details.csv","filename":"glycan_image_details.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_image_details.stat.csv","filename":"glycan_image_details.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-20T14:45:11.902693","modified":"2024-05-17T11:24:02.015Z","version":"v-0.0.0","name":"Glycan Images Details"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","images","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides details (such as image size, image notation, image style, image format)for the glycan (identified by GlyTouCan accession) images used in GlyGen. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)"],"object_id":"https://biocomputeobject.org/GLY_000477/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2998e25db51fcf4adeaf7eb938b51e02ce9c61e866df55d42ea0e52f08d4bec0","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":288,"last_update":"2024-05-17T11:24:02.015283Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000477/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"images.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/images.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_image_details.csv","filename":"glycan_image_details.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_image_details.stat.csv","filename":"glycan_image_details.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-20T14:45:11.902693","modified":"2022-09-26T09:05:56.531976","version":"v-2.0.2","name":"Glycan Images Details"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","images","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/images.tsv","filename":"images.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_image_details.csv","filename":"glycan_image_details.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides details (such as image size, image notation, image style, image format)for the glycan (identified by GlyTouCan accession) images used in GlyGen. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)"],"object_id":"https://biocomputeobject.org/GLY_000477/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2cce2fedb3712821ebc1b6c742b91cb6a5ea8d0a767a7034a1eeaef2e51fefa0","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.910000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000477/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"images.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/images.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_image_details.csv","filename":"glycan_image_details.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_image_details.stat.csv","filename":"glycan_image_details.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-20T14:45:11.902693","modified":"2022-09-26T09:05:56.531976","version":"v-2.1.1","name":"Glycan Images Details"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","images","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/images.tsv","filename":"images.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_image_details.csv","filename":"glycan_image_details.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides details (such as image size, image notation, image style, image format)for the glycan (identified by GlyTouCan accession) images used in GlyGen. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)"],"object_id":"https://biocomputeobject.org/GLY_000477/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6dbb066c574fe4e215202798959768a1","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:48.505000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000478/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000478/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"subsumption","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Subsumption","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-20T15:34:55.646138","modified":"2024-05-17T11:24:02.053Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Subsumption","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides relationship between the glycans (identified by the GlyTouCan accession). The relation is categorized as either Ancestor, Descendant, SubsumedBy or Subsumes. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"etag":"dd4a283ff3a6261ec9e7bc07d8553559ae60f94b0f42156cb893624fc43b66a2","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_subsumption.csv","filename":"glycan_subsumption.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_subsumption.stat.csv","filename":"glycan_subsumption.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":302,"last_update":"2024-05-17T11:24:02.053463Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000478/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000478/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"subsumption","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Subsumption","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-20T15:34:55.646138","modified":"2022-09-26T09:05:56.435169","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Subsumption","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/subsumption.tsv","filename":"subsumption.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_subsumption.csv","filename":"glycan_subsumption.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides relationship between the glycans (identified by the GlyTouCan accession). The relation is categorized as either Ancestor, Descendant, SubsumedBy or Subsumes. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"etag":"6a47942ac3ddd6996f111ae480532b33544558a2390ea5d227270fcb04d4f1ca","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"subsumption.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_subsumption.csv","filename":"glycan_subsumption.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_subsumption.stat.csv","filename":"glycan_subsumption.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.116000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000478/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000478/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"subsumption","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Subsumption","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-20T15:34:55.646138","modified":"2022-09-26T09:05:56.435169","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Subsumption","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/subsumption.tsv","filename":"subsumption.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_subsumption.csv","filename":"glycan_subsumption.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides relationship between the glycans (identified by the GlyTouCan accession). The relation is categorized as either Ancestor, Descendant, SubsumedBy or Subsumes. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"etag":"3b0d05405521eb39fe43c425fab8db1b","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"subsumption.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_subsumption.csv","filename":"glycan_subsumption.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_subsumption.stat.csv","filename":"glycan_subsumption.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:48.695000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000479/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000479/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fddba2f6afabe57d5519d16ffbd645ce3ce2549dc0c5c9811db45fc345134583","provenance_domain":{"name":"Glycosylation Sites - UniCarbKB [SARS CoV 2 proteins]","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-20T16:02:18.234465","modified":"2024-12-05T19:03:31.064Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["List of Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2 or 2019-nCoV) [taxid:2697049] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000434)"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was received directly from the provider (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}],"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":523,"last_update":"2024-12-05T19:03:31.064979Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000479/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000479/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation Sites - UniCarbKB [SARS CoV 2 proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-20T16:02:18.234465","modified":"2022-09-26T09:05:56.432366","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/crispin_azadi_yang_covid.csv","filename":"crispin_azadi_yang_covid.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was received directly from the provider (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of SARS coronavirus (SARS-CoV-2 or 2019-nCoV) [taxid:2697049] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000434)"],"etag":"bdb81f392857964112a5caff559e80ebcaa35ff474f84f412229f08bbd9a8674","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.896000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000479/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000479/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation Sites - UniCarbKB [SARS CoV 2 proteins]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-20T16:02:18.234465","modified":"2022-09-26T09:05:56.432366","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/crispin_azadi_yang_covid.csv","filename":"crispin_azadi_yang_covid.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/classification.tsv","filename":"classification.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/aadict.csv","filename":"aadict.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was received directly from the provider (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of SARS coronavirus (SARS-CoV-2 or 2019-nCoV) [taxid:2697049] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000434)"],"etag":"7a08f853ac0a703b0ae423213435b498","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:48.881000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000480/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000480/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites [GPTwiki]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Radoslav Goldman","email":"rg26@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-20T16:33:02.961632","modified":"2024-05-17T11:24:02.137Z","version":"v-0.0.0"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","GPTwiki","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the first column (UniProt) to UniProtKB canonical accession 2. Validate the Site and AminoAcid column with the canonical .fasta sequences. 3. Split the rows if the last column (Glycopeptides) has multiple values (separated by | ) 4. Add a new column for \"database\" with value \"GPTwiki\""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Human Glycosylation Sites [GPTwiki], provided by the Clinical and Translational Glycoscience Research Center (CTGRC), Georgetown University. The database contains list of human [taxid:9606] proteins with information on glycosylation sites and associated glycans from GPTwiki database [https://edwardslab.bmcb.georgetown.edu/gptwiki/Main_Page]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"etag":"25282747c154b06fd0c6a4492eb42eaf416af351e3939af9d3db692eea6c1ea2","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.stat.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":471,"last_update":"2024-05-17T11:24:02.137179Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000480/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000480/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites [GPTwiki]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Radoslav Goldman","email":"rg26@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-20T16:33:02.961632","modified":"2022-09-26T09:05:56.429819","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","GPTwiki","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycosites.csv","filename":"glycosites.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the first column (UniProt) to UniProtKB canonical accession 2. Validate the Site and AminoAcid column with the canonical .fasta sequences. 3. Split the rows if the last column (Glycopeptides) has multiple values (separated by | ) 4. Add a new column for \"database\" with value \"GPTwiki\""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Human Glycosylation Sites [GPTwiki], provided by the Clinical and Translational Glycoscience Research Center (CTGRC), Georgetown University. The database contains list of human [taxid:9606] proteins with information on glycosylation sites and associated glycans from GPTwiki database [https://edwardslab.bmcb.georgetown.edu/gptwiki/Main_Page]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"etag":"ac7e10e84bc278c91eb9b66c1b8d43da0f081d12876e73f94570ef2851913d3b","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"glycosites.csv","uri":"https:/data.glygen.org/ln2downloads/gptwiki/gpt_2021_06_23_14_51_10/glycosites.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.stat.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.912000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000480/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000480/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites [GPTwiki]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Radoslav Goldman","email":"rg26@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-20T16:33:02.961632","modified":"2022-09-26T09:05:56.429819","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","GPTwiki","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycosites.csv","filename":"glycosites.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the first column (UniProt) to UniProtKB canonical accession 2. Validate the Site and AminoAcid column with the canonical .fasta sequences. 3. Split the rows if the last column (Glycopeptides) has multiple values (separated by | ) 4. Add a new column for \"database\" with value \"GPTwiki\""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Human Glycosylation Sites [GPTwiki], provided by the Clinical and Translational Glycoscience Research Center (CTGRC), Georgetown University. The database contains list of human [taxid:9606] proteins with information on glycosylation sites and associated glycans from GPTwiki database [https://edwardslab.bmcb.georgetown.edu/gptwiki/Main_Page]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"etag":"cacb0d3dcee00371a34664d385286dea","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"glycosites.csv","uri":"/data/shared/glyds/downloads/gptwiki/gpt_2021_06_23_14_51_10/glycosites.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.stat.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:49.072000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000481/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000481/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"74a9422385b470196828c17adbe8d1b41e81458b368b90f0a081a444fad67cb9","provenance_domain":{"name":"Human Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-20T16:47:37.482643","modified":"2025-04-15T13:26:26.982Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Homo sapiens [taxid:9606] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tools 'RLIMS-G' developed by Dr. Vijay Shanker (University of Delaware) and 'GlycoSiteMiner'. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000001)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":585,"last_update":"2025-04-15T13:26:26.982973Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000481/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000481/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-20T16:47:37.482643","modified":"2022-09-26T09:05:56.438739","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"etag":"09a91977ca3e8b6014674ab4c400e397f8f7b6cfae3c348b613a4d2938993aea","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.918000Z","access_count":30},{"object_id":"https://biocomputeobject.org/GLY_000481/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000481/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-20T16:47:37.482643","modified":"2022-09-26T09:05:56.438739","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"etag":"a39457a9916a61f225e9edd7d881705a","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/shared/glyds/downloads/lit_min/2021_04_08/proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:49.261000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000482/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000482/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cd8479fde7be7fed66556561e2c74dc8c422cbb9381da25a65d186c5e18dfa69","provenance_domain":{"name":"SARS CoV 2 Proteoform Citations (UniCarbKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-20T17:08:49.084209","modified":"2024-12-05T19:17:51.633Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Citation details (such as title, journal_name, publication_date, authors) corresponding to the Digital Object Identifiers (DOI)/PMID present in dataset https://data.glygen.org/GLYDS000479"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The DOI(s) were extracted from dataset https://data.glygen.org/GLYDS000479. The corresponding details were manually compiled by the provider. "}],"keywords":["Proteins","DOI (Digital Object Identifier)"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":229,"last_update":"2024-12-05T19:17:51.633801Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000482/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000482/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Citation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS CoV 2 Proteoform Citations (UniCarbKB)","contributors":[{"affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-20T17:08:49.084209","modified":"2022-09-26T09:05:56.539956","version":"v-2.0.2"},"description_domain":{"keywords":["Proteins","DOI (Digital Object Identifier)"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/sarscov2_protein_citations_unicarbkb_literature.csv","filename":"sarscov2_protein_citations_unicarbkb_literature.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_unicarbkb.csv","filename":"sarscov2_proteoform_citations_unicarbkb.csv"}],"prerequisite":[],"description":"The DOI(s) were extracted from dataset https://data.glygen.org/GLYDS000479. The corresponding details were manually compiled by the provider. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Citation details (such as title, journal_name, publication_date, authors) corresponding to the Digital Object Identifiers (DOI)/PMID present in dataset https://data.glygen.org/GLYDS000479"],"etag":"a64a198fde5c49ce00a19df90cde2d79536b84eb41a4f33318e64f590324af28","io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/doi_citations.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov2_proteoform_citations_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_unicarbkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_unicarbkb.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_unicarbkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.926000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000482/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000482/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d2ab8fb9dd6a6c275a81813acdedde4a","provenance_domain":{"name":"SARS CoV 2 Proteoform Citations (UniCarbKB)","version":"v-2.1.1","created":"2020-04-20T17:08:49.084209","modified":"2023-03-14T16:35:20.027Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Citation details (such as title, journal_name, publication_date, authors) corresponding to the Digital Object Identifiers (DOI)/PMID present in dataset https://data.glygen.org/GLYDS000479"],"description_domain":{"keywords":["Proteins","DOI (Digital Object Identifier)"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/sarscov2_protein_citations_unicarbkb_literature.csv","filename":"sarscov2_protein_citations_unicarbkb_literature.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_unicarbkb.csv","filename":"sarscov2_proteoform_citations_unicarbkb.csv"}],"prerequisite":[],"description":"The DOI(s) were extracted from dataset https://data.glygen.org/GLYDS000479. The corresponding details were manually compiled by the provider. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/doi_citations.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov2_proteoform_citations_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Citation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:49.453000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000483/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000483/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4d1f9133bd7519ac39cd9112c6769293e43526074457b483b4e4d26aaf343848","provenance_domain":{"name":"Human Proteoform Citations (GlyConnect)","version":"v-0.0.0","created":"2020-04-28T10:49:06.505148","modified":"2024-05-17T11:24:02.257Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":440,"last_update":"2024-05-17T11:24:02.257063Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000483/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000483/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (GlyConnect)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-28T10:49:06.505148","modified":"2022-09-26T09:05:56.554000","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_glyconnect.csv","filename":"human_proteoform_citations_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"etag":"a57881b6ba79f30c03b29b68c6ff8be3d8aecd04090b71fb795f56ba89550a4c","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_glyconnect.csv","filename":"human_proteoform_citations_glycosylation_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_glyconnect.stat.csv","filename":"human_proteoform_citations_glycosylation_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.341000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000483/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000483/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c4f7a1e0c8f40320d276bee7fc235cc5","provenance_domain":{"name":"Human Proteoform Citations (GlyConnect)","version":"v-2.1.1","created":"2020-04-28T10:49:06.505148","modified":"2023-03-14T16:36:45.444Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_citations_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:49.644000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000484/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000484/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4b967208ca656440ee87179cc999a9c8618d8833065df14dae98f081c7c52830","provenance_domain":{"name":"Mouse Proteoform Citations (GlyConnect)","version":"v-0.0.0","created":"2020-04-28T11:04:45.973121","modified":"2024-05-17T11:24:02.295Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":440,"last_update":"2024-05-17T11:24:02.295476Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000484/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000484/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteoform Citations (GlyConnect)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-28T11:04:45.973121","modified":"2022-09-26T09:05:56.495361","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glyconnect.csv","filename":"mouse_proteoform_citations_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"etag":"2faa4d19dfaf733d0a49d3e708e0dc516d847cf55d3a292cf992ac8a4f16a042","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_glyconnect.csv","filename":"mouse_proteoform_citations_glycosylation_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_glyconnect.stat.csv","filename":"mouse_proteoform_citations_glycosylation_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.626000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000484/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000484/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d04cdf5263945940c22351693a3c9933","provenance_domain":{"name":"Mouse Proteoform Citations (GlyConnect)","version":"v-2.1.1","created":"2020-04-28T11:04:45.973121","modified":"2023-03-14T16:39:31.072Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:49.858000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000485/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000485/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"71cea7b89bc85774079ac62f8838a879a0ae4c742378cb1909de58a6288261fa","provenance_domain":{"name":"Rat Proteoform Citations (GlyConnect)","version":"v-0.0.0","created":"2020-04-28T11:07:38.533264","modified":"2024-05-17T11:24:02.335Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":438,"last_update":"2024-05-17T11:24:02.335219Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000485/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000485/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteoform Citations (GlyConnect)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-28T11:07:38.533264","modified":"2022-09-26T09:05:56.526933","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glyconnect.csv","filename":"rat_proteoform_citations_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"etag":"657e928e9958bc9e1b87a9741b1564259b146b60824575b9be4e567d01784785","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_glyconnect.csv","filename":"rat_proteoform_citations_glycosylation_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_glyconnect.stat.csv","filename":"rat_proteoform_citations_glycosylation_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.365000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000485/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000485/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9700d048b7e2e7df13fe2fc43e36346a","provenance_domain":{"name":"Rat Proteoform Citations (GlyConnect)","version":"v-2.1.1","created":"2020-04-28T11:07:38.533264","modified":"2023-03-14T16:40:38.516Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:50.053000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000487/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000487/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-29T16:14:08.766000","modified":"2024-05-17T11:24:02.372Z","version":"v-0.0.0"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a Protein Diseases dataset contains diseases caused by Hepatitis C virus (isolate H77) [taxid:63746] and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease Ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"etag":"782584f68321eaccbd1b4096d84a98b8c8d45a0fafd653a8d41d393bbef53201","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_disease_glygen.csv","filename":"hcv1a_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_disease_glygen.stat.csv","filename":"hcv1a_protein_disease_glygen.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":404,"last_update":"2024-05-17T11:24:02.372671Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000487/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000487/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-29T16:14:08.766000","modified":"2022-09-26T09:05:56.486763","version":"v-2.0.2"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Diseases dataset contains disease caused by hcv1a virus [taxid:11108] which is Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"etag":"0c36a6022cd82fb1f0de04b572ade2f2f6d34003827298269e3dca323fc127cc","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/hcv1a_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_disease_glygen.csv","filename":"hcv1a_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_disease_glygen.stat.csv","filename":"hcv1a_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.419000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000487/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000487/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-29T16:14:08.766000","modified":"2022-09-26T09:05:56.486763","version":"v-2.1.1"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Diseases dataset contains disease caused by hcv1a virus [taxid:11108] which is Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"etag":"a5a47e03fdb6a49d2696c2afb95a8c49","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/hcv1a_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_disease_glygen.csv","filename":"hcv1a_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_disease_glygen.stat.csv","filename":"hcv1a_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:50.247000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000488/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000488/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-29T16:14:59.174043","modified":"2024-05-17T11:24:02.415Z","version":"v-0.0.0"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Diseases dataset contains disease caused by hcv1b virus [taxid:11116] which is Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"etag":"907db1b7c954e933d23f31ae0eacbfa2cf19a146f24e3a8ba149b9f871bcae47","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_disease_glygen.csv","filename":"hcv1b_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_disease_glygen.stat.csv","filename":"hcv1b_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":494,"last_update":"2024-05-17T11:24:02.415586Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000488/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000488/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-29T16:14:59.174043","modified":"2022-09-26T09:05:56.508180","version":"v-2.0.2"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Diseases dataset contains disease caused by hcv1b virus [taxid:11116] which is Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"etag":"352b10d00e752ac867bc6fc8b2b0034c9ffe0fcab2a1cc164903b70809c8fe1a","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/hcv1b_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_disease_glygen.csv","filename":"hcv1b_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_disease_glygen.stat.csv","filename":"hcv1b_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:53.562000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000488/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000488/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-29T16:14:59.174043","modified":"2022-09-26T09:05:56.508180","version":"v-2.1.1"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Diseases dataset contains disease caused by hcv1b virus [taxid:11116] which is Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"etag":"5c0f43d0e3088bbfa78ab756e07b21e5","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/hcv1b_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_disease_glygen.csv","filename":"hcv1b_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_disease_glygen.stat.csv","filename":"hcv1b_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:50.434000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000489/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000489/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-29T16:15:30.138920","modified":"2024-05-17T11:24:02.454Z","version":"v-0.0.0"},"description_domain":{"keywords":["SARS (Severe Acute Respiratory Syndrome) ","DOID","SARS-CoV-1","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Diseases dataset contains disease caused by sarscov1 virus [taxid:694009] which is SARS and is mapped to all UniProtKB canonical accessions. The dataset contains SARS (Severe Acute Respiratory Syndrome) disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"02eff079d9bb1d86eff5eca398b42d11402b1a1938c6ca7aa0c6bd90f78f0ff6","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_disease_glygen.csv","filename":"sarscov1_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_disease_glygen.stat.csv","filename":"sarscov1_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":422,"last_update":"2024-05-17T11:24:02.454100Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000489/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000489/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-29T16:15:30.138920","modified":"2022-09-26T09:05:56.511806","version":"v-2.0.2"},"description_domain":{"keywords":["SARS (Severe Acute Respiratory Syndrome) ","DOID","SARS-CoV-1","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Diseases dataset contains disease caused by sarscov1 virus [taxid:694009] which is SARS and is mapped to all UniProtKB canonical accessions. The dataset contains SARS (Severe Acute Respiratory Syndrome) disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"960ba5c90be79803415c3f20907dfa95f25c42ee53457b29405ab8d4950ed3b5","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov1_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_disease_glygen.csv","filename":"sarscov1_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_disease_glygen.stat.csv","filename":"sarscov1_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.923000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000489/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000489/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-29T16:15:30.138920","modified":"2022-09-26T09:05:56.511806","version":"v-2.1.1"},"description_domain":{"keywords":["SARS (Severe Acute Respiratory Syndrome) ","DOID","SARS-CoV-1","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Diseases dataset contains disease caused by sarscov1 virus [taxid:694009] which is SARS and is mapped to all UniProtKB canonical accessions. The dataset contains SARS (Severe Acute Respiratory Syndrome) disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"a61f16ce6ad67f44d2fa3f266996fb53","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov1_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_disease_glygen.csv","filename":"sarscov1_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_disease_glygen.stat.csv","filename":"sarscov1_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:50.627000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000490/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000490/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-29T16:16:01.099167","modified":"2024-05-17T11:24:02.491Z","version":"v-0.0.0"},"description_domain":{"keywords":["COVID-19","DOID","SARS-CoV-2","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Diseases dataset contains disease caused by sarscov2 virus [taxid:2697049] which is COVID-19 mapped to all UniProtKB canonical accessions. The dataset contains COVID-19 disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"60de9a10cdf94aa40ab6768d124887f4353b54d921c5e631ee50b22f839fb5a5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_disease_glygen.csv","filename":"sarscov2_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_disease_glygen.stat.csv","filename":"sarscov2_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":401,"last_update":"2024-05-17T11:24:02.491802Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000490/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000490/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-29T16:16:01.099167","modified":"2022-09-26T09:05:56.462151","version":"v-2.0.2"},"description_domain":{"keywords":["COVID-19","DOID","SARS-CoV-2","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Diseases dataset contains disease caused by sarscov2 virus [taxid:2697049] which is COVID-19 mapped to all UniProtKB canonical accessions. The dataset contains COVID-19 disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"aad38b09d0b017e9b44ee436d9f47c4147a310fbb83fca69ba116824a3bcefdb","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov2_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_disease_glygen.csv","filename":"sarscov2_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_disease_glygen.stat.csv","filename":"sarscov2_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.496000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000490/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000490/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-29T16:16:01.099167","modified":"2022-09-26T09:05:56.462151","version":"v-2.1.1"},"description_domain":{"keywords":["COVID-19","DOID","SARS-CoV-2","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Diseases dataset contains disease caused by sarscov2 virus [taxid:2697049] which is COVID-19 mapped to all UniProtKB canonical accessions. The dataset contains COVID-19 disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"etag":"76059dad40e61c86c1c5d4dabf2fcf24","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_disease_glygen.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov2_protein_disease_glygen.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_disease_glygen.csv","filename":"sarscov2_protein_disease_glygen.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_disease_glygen.stat.csv","filename":"sarscov2_protein_disease_glygen.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:50.816000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000491/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000491/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (SVG format)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-04-29T16:23:27.495534","modified":"2024-05-17T11:24:02.527Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","svg"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-svg.tbz.?? > images-snfg-extended-svg.tbz 2. tar xvf images-snfg-extended-svg.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"2bdc02fe912d44702dc751c19daae8d0c3e6d93baf5d1519b0ebac9d3e41ded8","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_images_snfg_extended_svg.tar.gz","filename":"glycan_images_snfg_extended_svg.tar.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_images_snfg_extended_svg.tar.stat.csv","filename":"glycan_images_snfg_extended_svg.tar.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":245,"last_update":"2024-05-17T11:24:02.527623Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000491/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000491/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (SVG format)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-04-29T16:23:27.495534","modified":"2022-09-26T09:05:56.483383","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","svg"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/images-snfg-extended-svg.tbz.00","filename":"images-snfg-extended-svg.tbz.00"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/images-snfg-extended-svg.tbz.01","filename":"images-snfg-extended-svg.tbz.01"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_images_snfg_extended_svg.tar.gz","filename":"glycan_images_snfg_extended_svg.tar.gz"}],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-svg.tbz.?? > images-snfg-extended-svg.tbz 2. tar xvf images-snfg-extended-svg.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"806520b5a7f3d39a780fdf82eecdc5915b0db02ce7f4b919c102b6752995388a","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_images_snfg_extended_svg.tar.gz","filename":"glycan_images_snfg_extended_svg.tar.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_images_snfg_extended_svg.tar.stat.csv","filename":"glycan_images_snfg_extended_svg.tar.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.344000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000491/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000491/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (SVG format)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-04-29T16:23:27.495534","modified":"2022-09-26T09:05:56.483383","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","svg"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/images-snfg-extended-svg.tbz.00","filename":"images-snfg-extended-svg.tbz.00"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/images-snfg-extended-svg.tbz.01","filename":"images-snfg-extended-svg.tbz.01"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_images_snfg_extended_svg.tar.gz","filename":"glycan_images_snfg_extended_svg.tar.gz"}],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-svg.tbz.?? > images-snfg-extended-svg.tbz 2. tar xvf images-snfg-extended-svg.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"etag":"97abfc45a566dc869473569b505e601e","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_images_snfg_extended_svg.tar.gz","filename":"glycan_images_snfg_extended_svg.tar.gz"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_images_snfg_extended_svg.tar.stat.csv","filename":"glycan_images_snfg_extended_svg.tar.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:51.008000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000492/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000492/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"96e17ff8fba720d9099ff3ee3631ccab3d0dd69d2540affc32a1178c98a44a75","provenance_domain":{"name":"Mouse Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-30T10:27:18.537975","modified":"2025-04-15T13:29:14.041Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Mus musculus [taxid:10090] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tools 'RLIMS-G' developed by Dr. Vijay Shanker (University of Delaware) and 'GlycoSiteMiner' developed by the GlyGen team (https://github.com/glygener/glycositeminer). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000007)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":675,"last_update":"2025-04-15T13:29:14.041607Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000492/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-30T10:27:18.537975","modified":"2022-09-26T09:05:56.493570","version":"v-2.0.2","name":"Mouse Glycosylation Sites [Automatic Literature Mining] [Automatically verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000492/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0f7215903a636b77234b15cd7757d2a4f9f6e8399861cdabf7f9aaf2c15c8194"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.185000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000492/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/shared/glyds/downloads/lit_min/2021_04_08/proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-30T10:27:18.537975","modified":"2022-09-26T09:05:56.493570","version":"v-2.1.1","name":"Mouse Glycosylation Sites [Automatic Literature Mining] [Automatically verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000492/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"054c6479f302f5ff1fd370d38e4ab23e"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:51.203000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000493/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000493/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"24885b02ca928431938a5596df725d511a7b9ee1e8becf566e0cd6dd6501a356","provenance_domain":{"name":"Rat Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-30T10:34:38.124446","modified":"2025-04-15T13:37:28.428Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Rattus norvegicus [taxid:10116] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tools 'RLIMS-G' developed by Dr. Vijay Shanker (University of Delaware) and 'GlycoSiteMiner' developed by the GlyGen team (https://github.com/glygener/glycositeminer). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000244)"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":678,"last_update":"2025-04-15T13:37:28.428939Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000493/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"George Washington University","contribution":["contributedBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-30T10:34:38.124446","modified":"2022-09-26T09:05:56.528609","version":"v-2.0.2","name":"Rat Glycosylation Sites [Automatic Literature Mining] [Automatically verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000493/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6513b161345dd470103473cc1453309f199d2b953b3448d3856172a637893704"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.731000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000493/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/shared/glyds/downloads/lit_min/2021_04_08/proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-30T10:34:38.124446","modified":"2022-09-26T09:05:56.528609","version":"v-2.1.1","name":"Rat Glycosylation Sites [Automatic Literature Mining] [Automatically verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000493/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"633c6742d7ab6a833e7c4766f05534d3"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:51.406000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000494/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000494/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"HCV1a Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-05-07T18:11:47.601071","modified":"2024-05-17T11:24:02.641Z","version":"v-0.0.0"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The HCV1a Protein Site Annotation (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"4595c97612b800f6d45e6122c120cfea9cd76bdce52919299f550e389872115f","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":332,"last_update":"2024-05-17T11:24:02.641273Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000494/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000494/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1a Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-05-07T18:11:47.601071","modified":"2022-09-26T09:05:56.537576","version":"v-2.0.2"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Site Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"f02ecfe57e682010e7bcc8220a62c2c8671b02e7110addef594b22932202e0b7","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.836000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000494/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000494/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1a Protein Site Annotation","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-05-07T18:11:47.601071","modified":"2022-09-26T09:05:56.537576","version":"v-2.1.1"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Site Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen. "],"etag":"ed66fed26e9faed7d7a8170bf694b625","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:51.598000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000495/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000495/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Glycosylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-05-07T18:18:49.168950","modified":"2024-06-03T21:23:04.264Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Glycosylation Sites (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"f8621a2c2593048e41be9c4d0f44d5f63ab56cdedc2ca1f3a88df0eb2f15ef01","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-06-03T21:23:04.264466Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000495/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000495/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Glycosylation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-05-07T18:18:49.168950","modified":"2022-09-26T09:05:56.555699","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Glycosylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"9db5178820bff7efa1f096dd939058b24b0042c7ed21fb2539d4e9a7f9edd0df","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.247000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000495/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000495/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 Glycosylation Sites (UniProtKB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-05-07T18:18:49.168950","modified":"2022-09-26T09:05:56.555699","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-coronavirus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Glycosylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"0dc1158d9d773093ae9ac5b7f19493d4","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:51.789000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000496/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000496/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-05-07T18:25:16.830914","modified":"2024-06-03T21:23:29.901Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"107fcde4551cc9b307c097acc97e92ed7f052cb859513a96c8ef95886b39fc08","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_altnames.csv","filename":"sarscov2_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_altnames.stat.csv","filename":"sarscov2_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":298,"last_update":"2024-06-03T21:23:29.901062Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000496/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000496/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-05-07T18:25:16.830914","modified":"2022-09-26T09:05:56.434046","version":"v-2.0.2"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_altnames.csv","filename":"sarscov2_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for sarscov2 [taxid:2697049] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"d087644045fe188943bde7f9198592094e6aeaded0efac93637591eeab3301a6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_altnames.csv","filename":"sarscov2_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_altnames.stat.csv","filename":"sarscov2_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.416000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000496/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000496/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Alternative Name (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-05-07T18:25:16.830914","modified":"2022-09-26T09:05:56.434046","version":"v-2.1.1"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_altnames.csv","filename":"sarscov2_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for sarscov2 [taxid:2697049] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"1142755b45ee45b4b625d00170b6c65a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_altnames.csv","filename":"sarscov2_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_altnames.stat.csv","filename":"sarscov2_protein_altnames.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:51.978000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000497/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000497/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Byonic","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"Homo sapiens","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"N-linked Byonic Glycan [Human]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-05-12T18:50:02.969226","modified":"2024-05-17T11:24:02.749Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Byonic"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the byonic format of n-linked human glycans (identified by GlyTouCan Ac.). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/. "],"etag":"928e652bfa8d80d1e6504a4987ba512e1ff6ae34e00089a58001433e1404aaf4","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_type_n_linked_byonic.csv","filename":"glycan_type_n_linked_byonic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_type_n_linked_byonic.stat.csv","filename":"glycan_type_n_linked_byonic.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":261,"last_update":"2024-05-17T11:24:02.749583Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000497/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000497/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Byonic","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"N-linked Byonic Glycan [Human]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-05-12T18:50:02.969226","modified":"2022-09-26T09:05:56.436251","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Byonic"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/type_n_linked_byonic.tsv","filename":"type_n_linked_byonic.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_type_n_linked_byonic.csv","filename":"glycan_type_n_linked_byonic.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the byonic format of n-linked human glycans (identified by GlyTouCan Ac.). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/. "],"etag":"abc4961df78409fe061df1e27610af356a1bc3bb34060ca559ef9e097ace1e7a","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"byonic_glygen_human_nlinked.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/byonic_glygen_human_nlinked.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_type_n_linked_byonic.csv","filename":"glycan_type_n_linked_byonic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_type_n_linked_byonic.stat.csv","filename":"glycan_type_n_linked_byonic.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.099000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000497/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000497/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Byonic","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"Homo sapiens","category_name":"species"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"N-linked Byonic Glycan [Human]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-05-12T18:50:02.969226","modified":"2022-09-26T09:05:56.436251","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Byonic"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/type_n_linked_byonic.tsv","filename":"type_n_linked_byonic.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_type_n_linked_byonic.csv","filename":"glycan_type_n_linked_byonic.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the byonic format of n-linked human glycans (identified by GlyTouCan Ac.). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/. "],"etag":"ed2a24f2b4ca260f6ddba1b626ec1b46","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"byonic_glygen_human_nlinked.txt","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/byonic_glygen_human_nlinked.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_type_n_linked_byonic.csv","filename":"glycan_type_n_linked_byonic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_type_n_linked_byonic.stat.csv","filename":"glycan_type_n_linked_byonic.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:52.170000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000498/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000498/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Human]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-05-13T10:38:59.901723","modified":"2024-05-21T15:26:55.850Z","version":"v-0.0.0"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for human [taxid:9606] proteins (https://data.glygen.org/GLY_000040: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197, https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB human glycoprotein dataset (https://data.glygen.org/GLY_000040: v-1.4.5 09/13/2019). "],"etag":"8a324244ddf238d9b1658fe48fd00b6a0b5b75d69249f75af3193cfa3e7ee17d","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_pro_annotation.csv","filename":"human_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_pro_annotation.stat.csv","filename":"human_protein_pro_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":603,"last_update":"2024-05-21T15:26:55.850327Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000498/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000498/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Human]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-05-13T10:38:59.901723","modified":"2022-09-26T09:05:56.530713","version":"v-2.0.2"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_pro_annotation.csv","filename":"human_protein_pro_annotation.csv"}],"prerequisite":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for human [taxid:9606] proteins (https://data.glygen.org/GLYDS000040: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197, https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB human glycoprotein dataset (https://data.glygen.org/GLYDS000040: v-1.4.5 09/13/2019). "],"etag":"839194ba951c84eb0c5187006c531e51bca810b1018e2c79ef053ef9fe17827f","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"https:/data.glygen.org/ln2downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_pro_annotation.csv","filename":"human_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_pro_annotation.stat.csv","filename":"human_protein_pro_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.165000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000498/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000498/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Human]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-05-13T10:38:59.901723","modified":"2022-09-26T09:05:56.530713","version":"v-2.1.1"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_pro_annotation.csv","filename":"human_protein_pro_annotation.csv"}],"prerequisite":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for human [taxid:9606] proteins (https://data.glygen.org/GLYDS000040: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197, https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB human glycoprotein dataset (https://data.glygen.org/GLYDS000040: v-1.4.5 09/13/2019). "],"etag":"ea33957bf96acd30589bf9132610172b","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"/data/shared/glyds/downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_pro_annotation.csv","filename":"human_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_pro_annotation.stat.csv","filename":"human_protein_pro_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:52.362000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000499/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000499/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"66b78c09aa8fe076ca05423f8c36bf937f433e8bf14bf7a912f02d246ac331a6","provenance_domain":{"name":"GlyGen-PubChem Protein Crossreferences Mapping","version":"v-0.0.0","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2020-06-04T09:25:12.224023","modified":"2026-08-19T16:49:46.902Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The GlyGen-PubChem Protein Cross-references dataset contains UniProtKB canonical glycoprotein accessions from all GlyGen species for the purpose of PubChem Protein to GlyGen cross-references. In the dataset, the UniProtKB glycoprotein accessions are mapped to the RefSeq accessions and glycosylation annotation corresponding to glycoprotein have been added. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse, rat, hcv1a, hcv1b, sarscov1 and sarscov2 species and maps it to the refseq accessions and adds the corresponding glycosylation annotation to extract it into a csv dataset file. "}],"keywords":["PubChem Protein","GlyGen","crossreferences","human","mouse","rat","hcv1a","hcv1b","sarscov1","sarscov2","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_pubchem_xref_mapping.csv","filename":"protein_glygen_pubchem_xref_mapping.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_pubchem_xref_mapping.stat.csv","filename":"protein_glygen_pubchem_xref_mapping.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PubChem Protein Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":788,"last_update":"2026-08-19T16:49:46.902914Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000499/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000499/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PubChem Protein Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"GlyGen-PubChem Protein Crossreferences Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-06-04T09:25:12.224023","modified":"2022-09-26T09:05:56.563491","version":"v-2.0.2"},"description_domain":{"keywords":["PubChem Protein","GlyGen","crossreferences","human","mouse","rat","hcv1a","hcv1b","sarscov1","sarscov2","NCBI RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"http://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_unicarbkb_literature.csv","filename":"sarscov2_proteoform_citations_unicarbkb_literature.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse, rat, hcv1a, hcv1b, sarscov1 and sarscov2 species and maps it to the refseq accessions and adds the corresponding glycosylation annotation to extract it into a csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The GlyGen-PubChem Protein Cross-references dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of PubChem Protein to GlyGen cross-references. In the dataset, the UniProtKB glycoprotein accessions are mapped to the RefSeq accessions and glycosylation annotation corresponding to glycoprotein have been added. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen. "],"etag":"c5804c9f46ccb46f8938687e04b272cabe56a34103d3aad03abcf88b21a507c1","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_pubchem_xref_mapping.csv","filename":"protein_glygen_pubchem_xref_mapping.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_pubchem_xref_mapping.stat.csv","filename":"protein_glygen_pubchem_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.104000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000499/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000499/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PubChem Protein Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"GlyGen-PubChem Protein Crossreferences Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-06-04T09:25:12.224023","modified":"2022-09-26T09:05:56.563491","version":"v-2.1.1"},"description_domain":{"keywords":["PubChem Protein","GlyGen","crossreferences","human","mouse","rat","hcv1a","hcv1b","sarscov1","sarscov2","NCBI RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"http://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_unicarbkb_literature.csv","filename":"sarscov2_proteoform_citations_unicarbkb_literature.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"uri":"mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse, rat, hcv1a, hcv1b, sarscov1 and sarscov2 species and maps it to the refseq accessions and adds the corresponding glycosylation annotation to extract it into a csv dataset file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The GlyGen-PubChem Protein Cross-references dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of PubChem Protein to GlyGen cross-references. In the dataset, the UniProtKB glycoprotein accessions are mapped to the RefSeq accessions and glycosylation annotation corresponding to glycoprotein have been added. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen. "],"etag":"bfa2ae30fa986030ac18c20b443ef7d0","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_pubchem_xref_mapping.csv","filename":"protein_glygen_pubchem_xref_mapping.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_pubchem_xref_mapping.stat.csv","filename":"protein_glygen_pubchem_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:52.561000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000507/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000507/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"The George Washington University","name":"Human Cancer Mutation LOG and GOG effect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-06-25T13:28:50.371628","modified":"2024-05-17T11:24:02.862Z","version":"v-0.0.0"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"a8bc7cfd3a322e0bfa7dbcdda3fcd22b44052603979482b0219ec6e5615f51e5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_cancer_glycoeffect.csv","filename":"human_protein_mutation_cancer_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_cancer_glycoeffect.stat.csv","filename":"human_protein_mutation_cancer_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:02.862172Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000507/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000507/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"The George Washington University","name":"Human Cancer Mutation LOG and GOG effect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-25T13:28:50.371628","modified":"2022-09-26T09:08:12.504427","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"c93779d17cb2b6e1e30db505102cf32939f086755b0ef1791df0410d04201ee3","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_cancer.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer_glycoeffect.csv","filename":"human_protein_mutation_cancer_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer_glycoeffect.stat.csv","filename":"human_protein_mutation_cancer_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.030000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000507/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000507/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"The George Washington University","name":"Human Cancer Mutation LOG and GOG effect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-06-25T13:28:50.371628","modified":"2022-09-26T09:08:12.504427","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"9663fc9cb02118c161d0ee2d1d7bd9ba","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_cancer.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer_glycoeffect.csv","filename":"human_protein_mutation_cancer_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer_glycoeffect.stat.csv","filename":"human_protein_mutation_cancer_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:52.752000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000508/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000508/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Germline Mutation LOG and GOG effect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-06-25T13:33:02.009109","modified":"2024-05-17T11:24:02.897Z","version":"v-0.0.0"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"ca2223c3b2927eb745f76929cbb653ded93e9faf02b10bd338ca36797a260091","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_germline_glycoeffect.csv","filename":"human_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_germline_glycoeffect.stat.csv","filename":"human_protein_mutation_germline_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:02.897759Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000508/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000508/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Germline Mutation LOG and GOG effect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-25T13:33:02.009109","modified":"2022-09-26T09:08:12.724774","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"0766f05776f3ce362e932d09b4181bab03856d34c04610f791e27cdf31c1be14","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_germline.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_germline_glycoeffect.csv","filename":"human_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_germline_glycoeffect.stat.csv","filename":"human_protein_mutation_germline_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.818000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000508/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000508/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Germline Mutation LOG and GOG effect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-06-25T13:33:02.009109","modified":"2022-09-26T09:08:12.724774","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"1400ea19506e7e6ed16f0da74c336618","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_germline.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_germline_glycoeffect.csv","filename":"human_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_germline_glycoeffect.stat.csv","filename":"human_protein_mutation_germline_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:52.947000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000509/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000509/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Somatic Mutations LOG and GOG effect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-06-25T13:37:33.727471","modified":"2024-05-17T11:24:02.934Z","version":"v-0.0.0"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"1248c3a26949476d555e80c1b8cf889fccd5645079c54b8eb92127d57907ffc1","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_somatic_glycoeffect.csv","filename":"human_protein_mutation_somatic_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_somatic_glycoeffect.stat.csv","filename":"human_protein_mutation_somatic_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:02.934498Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000509/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000509/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Somatic Mutations LOG and GOG effect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-25T13:37:33.727471","modified":"2022-09-26T09:08:12.758873","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"8f19a4e1163b9c9505491992b9bb357220a77184e85082d4a07678ca042a90f6","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_somatic.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_somatic.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_somatic_glycoeffect.csv","filename":"human_protein_mutation_somatic_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_somatic_glycoeffect.stat.csv","filename":"human_protein_mutation_somatic_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.230000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000509/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000509/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Somatic Mutations LOG and GOG effect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-06-25T13:37:33.727471","modified":"2022-09-26T09:08:12.758873","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"d1f253779f369a9fae6ae6f6bf0de133","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_somatic.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_somatic.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_somatic_glycoeffect.csv","filename":"human_protein_mutation_somatic_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_somatic_glycoeffect.stat.csv","filename":"human_protein_mutation_somatic_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:53.147000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000511/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000511/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"93eaaea7d6feac23ccdb1eacfc5cd38e53c80ed7baf92d4c64ca55caac96161e","provenance_domain":{"name":"Human Proteoform Citations (Literature)","version":"v-0.0.0","created":"2020-06-26T12:55:02.653766","modified":"2024-05-17T11:24:02.970Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Proteoform Citations (Literature) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000143. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.csv","filename":"human_proteoform_citations_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":272,"last_update":"2024-05-17T11:24:02.970503Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000511/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000511/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Literature)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-26T12:55:02.653766","modified":"2022-09-26T09:08:12.512126","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature.csv","filename":"human_proteoform_citations_glycosylation_literature.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Proteoform Citations (Literature) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000143. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"9793212140dea3f7b846dabcbcff14d0a089a45263e218d2c45d07e8d1fe73e2","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature.csv","filename":"human_proteoform_citations_glycosylation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature.stat.csv","filename":"human_proteoform_citations_glycosylation_literature.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.512000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000511/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000511/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"68cd2e9a8e76229a7c645f40108b9bf1","provenance_domain":{"name":"Human Proteoform Citations (Literature)","version":"v-2.1.1","created":"2020-06-26T12:55:02.653766","modified":"2023-03-14T16:41:27.538Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Proteoform Citations (Literature) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000143. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.csv","filename":"human_proteoform_citations_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.csv","filename":"human_proteoform_citations_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:53.342000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000512/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000512/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f734c22963aaf31d8ad5d48c1513d62fed3f4574d4c174906207429d26ee3186","provenance_domain":{"name":"HCV1a Proteoform Citations (Literature)","version":"v-0.0.0","created":"2020-06-26T15:07:28.950575","modified":"2024-05-17T11:24:03.008Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The HCV1a Proteoform Citations (Literature) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLY_000335. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.stat.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":271,"last_update":"2024-05-17T11:24:03.008123Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000512/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000512/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Proteoform Citations (Literature)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-26T15:07:28.950575","modified":"2022-09-26T09:08:12.738400","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_citations_glycosylation_literature.csv","filename":"hcv1a_proteoform_citations_glycosylation_literature.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000335. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"dd0ccd93244c1bb03ab1c4d43ed0366b68be850ed4556b99fa18b29118f1b8ef","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_citations_glycosylation_literature.csv","filename":"hcv1a_proteoform_citations_glycosylation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_citations_glycosylation_literature.stat.csv","filename":"hcv1a_proteoform_citations_glycosylation_literature.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.979000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000512/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000512/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e3a98b3213d8182c10d92b028fe89401","provenance_domain":{"name":"HCV1a Proteoform Citations (Literature)","version":"v-2.1.1","created":"2020-06-26T15:07:28.950575","modified":"2023-03-14T16:42:28.074Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000335. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.stat.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:53.541000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000513/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000513/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d5d617795ea106c2b813a383a83571bfb54a0f54e15eb1b17f4702496f72f2b1","provenance_domain":{"name":"Human Proteoform Citations (Harvard)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-06-26T15:19:23.571116","modified":"2024-08-05T12:27:04.913Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLY_000142. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_harvard.csv","filename":"human_proteoform_citations_glycosylation_sites_harvard.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_harvard.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_harvard.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":231,"last_update":"2024-08-05T12:27:04.913367Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000513/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000513/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Harvard)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-26T15:19:23.571116","modified":"2022-09-26T09:08:12.744366","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_harvard.csv","filename":"human_proteoform_citations_glycosylation_harvard.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000142. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"b2ed5827b0ca1b5b607d70cc818e1aceb91d2a8a0ca9f49e151c28b1beb97c49","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_harvard.csv","filename":"human_proteoform_citations_glycosylation_harvard.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_harvard.stat.csv","filename":"human_proteoform_citations_glycosylation_harvard.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.638000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000513/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000513/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3b11be6304f5e10861af8a33a5ed016e","provenance_domain":{"name":"Human Proteoform Citations (Harvard)","version":"v-2.1.1","created":"2020-06-26T15:19:23.571116","modified":"2023-03-14T16:43:09.964Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000142. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_harvard.csv","filename":"human_proteoform_citations_glycosylation_harvard.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_harvard.csv","filename":"human_proteoform_citations_glycosylation_sites_harvard.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_harvard.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_harvard.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:53.732000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000514/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000514/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e42049605e9281f697111c4a777deec93ade2cf2203cc8397ffa7e92290a7fe6","provenance_domain":{"name":"Human Proteoform Citations (Tyr O-linked)","version":"v-0.0.0","created":"2020-06-26T15:25:42.130665","modified":"2024-05-17T11:24:03.087Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file human_proteoform_glycosylation_sites_tyr_o_linked.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_tyr_o_linked.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_tyr_o_linked.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations (Tyr O-linked)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":250,"last_update":"2024-05-17T11:24:03.087136Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000514/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000514/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations (Tyr O-linked)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Tyr O-linked)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-26T15:25:42.130665","modified":"2022-09-26T09:08:12.670703","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_tyr_o_linked.csv","filename":"human_proteoform_citations_glycosylation_tyr_o_linked.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file human_proteoform_glycosylation_sites_tyr_o_linked.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"265a46943c36d313d5da0e5d3ef34cebfb1c96ee7714ca304553735d45b16b5b","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_tyr_o_linked.csv","filename":"human_proteoform_citations_glycosylation_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_tyr_o_linked.stat.csv","filename":"human_proteoform_citations_glycosylation_tyr_o_linked.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.424000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000514/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000514/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"caf2daa4d7c31772dbeb1b13b39c3fad","provenance_domain":{"name":"Human Proteoform Citations (Tyr O-linked)","version":"v-2.1.1","created":"2020-06-26T15:25:42.130665","modified":"2023-03-14T16:44:07.464Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file human_proteoform_glycosylation_sites_tyr_o_linked.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_tyr_o_linked.csv","filename":"human_proteoform_citations_glycosylation_tyr_o_linked.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_tyr_o_linked.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_tyr_o_linked.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations (Tyr O-linked)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:53.924000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000515/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000515/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1733ab09476f56add1f8ca7a4ec24f3e33bdc59bfce24aa146ca6c0e6a32fdf3","provenance_domain":{"name":"SARS CoV1 Proteoform Citations (Literature)","version":"v-0.0.0","created":"2020-06-26T15:27:32.833475","modified":"2024-05-17T11:24:03.125Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file sarscov1_proteoform_glycosylation_sites_literature.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":251,"last_update":"2024-05-17T11:24:03.125700Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000515/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000515/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS CoV1 Proteoform Citations (Literature)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-26T15:27:32.833475","modified":"2022-09-26T09:08:12.698867","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/","filename":""}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file sarscov1_proteoform_glycosylation_sites_literature.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"5354f133d43a44098c98f88fa2f881e26c30169dee90d1a836cd4cf7a69f46c7","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_literature.csv","filename":"sarscov1_proteoform_citations_glycosylation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_literature.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_literature.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.077000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000515/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000515/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e1fa9ae9bdef8fa6501c309c080b8c5f","provenance_domain":{"name":"SARS CoV1 Proteoform Citations (Literature)","version":"v-2.1.1","created":"2020-06-26T15:27:32.833475","modified":"2023-03-14T16:45:05.352Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file sarscov1_proteoform_glycosylation_sites_literature.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:54.112000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000516/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000516/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6956d8c31aa75ae9059df396b3a46596c2a08ae89473395c71b1a63186d2061a","provenance_domain":{"name":"Human Proteoform Citations (Literature Mining)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-06-26T15:29:27.375356","modified":"2025-04-15T14:23:00.332Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Proteoform Citations [Automatic Literature Mining] dataset contains Homo sapiens [taxid:9606] citation details of the publications present in the Human Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_000481)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":343,"last_update":"2025-04-15T14:23:00.332609Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000516/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000516/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Literature Mining)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-06-26T15:29:27.375356","modified":"2022-09-26T09:08:12.546021","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_citations_literature_mining.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature_mining.csv","filename":"human_proteoform_citations_glycosylation_literature_mining.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000481. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"0e6d8cb21eff94e3ff5ca5de78b90e2bd098e11b67d7d4e1e22369f9c0dd3eae","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature_mining.csv","filename":"human_proteoform_citations_glycosylation_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature_mining.stat.csv","filename":"human_proteoform_citations_glycosylation_literature_mining.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.781000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000516/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000516/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a75809703699d1bd6dbdc03714814224","provenance_domain":{"name":"Human Proteoform Citations (Literature Mining)","version":"v-2.1.1","created":"2020-06-26T15:29:27.375356","modified":"2023-03-14T16:46:00.376Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000481. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_citations_literature_mining.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_literature_mining.csv","filename":"human_proteoform_citations_glycosylation_literature_mining.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:54.308000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000517/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000517/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5ce7826ff89fa583792b562932157c37d21538e3597c78990f570d20a6a425bf","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Sites (MCW)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-07-09T13:50:43.000375","modified":"2024-12-03T18:14:08.581Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human O-GlcNAc Glycosylation Sites (MCW) contains Homo sapiens (taxid:9606) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The current dataset has 4997 proteins with O-GlcNAc modifications. Out of which 3262 proteins have no site information where as 1735 proteins have 6722 sites.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Human O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s human protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to human species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding human UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a total of 2,237 proteins had an O-GlcNAc score of 3 or under, meaning that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation.","The log file - https://data.glygen.org/ln2data/releases/data/v-1.12.3/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log contains the entries that were excluded from the output file along with the reason for exclusion.","The orginal unprocessed dataset in excel format can be found at https://figshare.com/articles/The_human_O-GlcNAcome_database/12443495/4"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field."}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":3626,"last_update":"2024-12-03T18:14:08.581035Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000517/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000517/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human O-GlcNAc Glycosylation Sites (MCW)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-07-09T13:50:43.000375","modified":"2022-09-26T09:08:12.645447","version":"v-2.0.2"},"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/human_o-glcnacome_mcw.csv","filename":"human_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.log"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Human O-GlcNAc Glycosylation Sites (MCW) contains human (taxid:9606) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The current dataset has 4997 proteins with O-GlcNAc modifications. Out of which 3262 proteins have no site information where as 1735 proteins have 6722 sites.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Human O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s human protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to human species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding human UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a total of 2,237 proteins had an O-GlcNAc score of 3 or under, meaning that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation.","The log file - https://data.glygen.org/ln2data/releases/data/v-1.12.3/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log contains the entries that were excluded from the output file along with the reason for exclusion.","The orginal unprocessed dataset in excel format can be found at https://figshare.com/articles/The_human_O-GlcNAcome_database/12443495/4"],"etag":"c38011e3dd16c6f930108307050ca52d9b4ac9d36ecf23e3049b387fe0260559","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_info_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_recnames.csv"}},{"uri":{"filename":"human_o-glcnacome_mcw.csv","uri":"https:/data.glygen.org/ln2downloads/mcw_oglcnac/2022_07_29/human_o-glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.318000Z","access_count":9},{"object_id":"https://biocomputeobject.org/GLY_000517/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000517/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"db1241aa853d611f042c504bf62a6476","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.1.1","created":"2020-07-09T13:50:43.000375","modified":"2023-03-14T16:47:56.758Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human O-GlcNAc Glycosylation Sites (MCW) contains human (taxid:9606) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The current dataset has 4997 proteins with O-GlcNAc modifications. Out of which 3262 proteins have no site information where as 1735 proteins have 6722 sites.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Human O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s human protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to human species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding human UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a total of 2,237 proteins had an O-GlcNAc score of 3 or under, meaning that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation.","The log file - https://data.glygen.org/ln2data/releases/data/v-1.12.3/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log contains the entries that were excluded from the output file along with the reason for exclusion.","The orginal unprocessed dataset in excel format can be found at https://figshare.com/articles/The_human_O-GlcNAcome_database/12443495/4"],"description_domain":{"keywords":["O-GlcNAc"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/human_o-glcnacome_mcw.csv","filename":"human_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.log"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_info_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"human_o_glcnacome_mcw.csv","uri":"/data/shared/glyds/downloads/mcw_oglcnac/2023_04/human_o_glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:54.493000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000518/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000518/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"36182d34d82788084aeb90761b4b33cc7f684b243c242cda8de0961101133656","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Citations (MCW)","version":"v-0.0.0","created":"2020-07-15T16:28:21.779974","modified":"2024-05-17T11:24:03.245Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Human O-GlcNAc Glycosylation Sites (MCW)  https://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":235,"last_update":"2024-05-17T11:24:03.245784Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000518/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000518/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human O-GlcNAc Glycosylation Citations (MCW)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-07-15T16:28:21.779974","modified":"2022-09-26T09:08:12.685341","version":"v-2.0.2"},"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_o_glcnac_mcw.csv","filename":"human_proteoform_citations_o_glcnac_mcw.csv"}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Human O-GlcNAc Glycosylation Sites (MCW)  https://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"etag":"ab74a4bbc8b2eb456b48404411a59cf03db2ab1c51bcdf8736a1bab350e1c09d","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"human_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv","filename":"human_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.612000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000518/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000518/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d6478bdd891fcb5e00afb0bfdd2c8031","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Citations (MCW)","version":"v-2.1.1","created":"2020-07-15T16:28:21.779974","modified":"2023-03-14T16:48:38.233Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Human O-GlcNAc Glycosylation Sites (MCW)  https://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_citations_glycosylation_sites_o_glcnac_mcw.csv"}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:54.689000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000519/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000519/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (iPTMNet)","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-08-17T16:43:14.212000","modified":"2024-05-21T14:45:28.794Z","version":"v-0.0.0"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The Human Phosphorylation Sites (iPTMNet) dataset contains Homo sapiens [taxid:9606] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"etag":"530fe2b1f3b4516a6942a32d942b72733f0b2abd028def5c2b6e9d3bfeeff7d9","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_phosphorylation_sites_iptmnet.csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":293,"last_update":"2024-05-21T14:45:28.794692Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000519/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000519/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (iPTMNet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-08-17T16:43:14.212000","modified":"2022-09-26T09:08:12.690030","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"417e53bbae9b79964d4d2337546438904fdf46c02288e8a3bd8a708fc45d524e","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"https:/data.glygen.org/ln2downloads/iptmnet/2022_02/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_phosphorylation_sites_iptmnet.csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.757000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000519/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000519/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (iPTMNet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-17T16:43:14.212000","modified":"2022-09-26T09:08:12.690030","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"982bb3fb5185c18797b9d9c65c547074","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"/data/shared/glyds/downloads/iptmnet/2023_05_22/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_phosphorylation_sites_iptmnet.csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:54.885000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000520/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000520/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Mouse Phosphorylation Sites (iPTMNet)","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-08-17T16:48:12.211710","modified":"2024-05-21T14:45:59.266Z","version":"v-0.0.0"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Phosphorylation Sites (iPTMNet) dataset contains Mus musculus [taxid:10090] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"etag":"942c342aaf5b8b8693327b5c97c29f0e59c882c9b7aa9705fa2876085192fc12","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":294,"last_update":"2024-05-21T14:45:59.266246Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000520/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000520/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Phosphorylation Sites (iPTMNet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-08-17T16:48:12.211710","modified":"2022-09-26T09:08:12.576310","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"d35a78b259369a959750b209b4aab4ec30495358366676c2632c56c470319478","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"https:/data.glygen.org/ln2downloads/iptmnet/2022_02/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.985000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000520/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000520/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Phosphorylation Sites (iPTMNet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-17T16:48:12.211710","modified":"2022-09-26T09:08:12.576310","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"82dcf4fc083807030e9f9a448ac50609","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"/data/shared/glyds/downloads/iptmnet/2023_05_22/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:55.069000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000521/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000521/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"41c71b6735f68f769732cdc8bba0d4133581d4a0552a40ed0b386995d92f8792","provenance_domain":{"name":"Rat Phosphorylation Sites (iPTMnet)","version":"v-0.0.0","created":"2020-08-17T16:58:50.536651","modified":"2025-10-09T14:13:12.824Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Phosphorylation Sites (iPTMNet) dataset contains Rattus norvegicus [taxid:10116] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2025-10-09T14:13:12.824994Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000521/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000521/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Phosphorylation Sites (iPTMnet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-08-17T16:58:50.536651","modified":"2022-09-26T09:08:12.590164","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"0b23690e01cead2fca36a62314fb55bf6d6ea0d4c60db9522ed269f2ef220c77","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"https:/data.glygen.org/ln2downloads/iptmnet/2022_02/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.601000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000521/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000521/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Phosphorylation Sites (iPTMnet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-17T16:58:50.536651","modified":"2022-09-26T09:08:12.590164","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"81d642846c3125bcc5b03acd0915a5ff","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"/data/shared/glyds/downloads/iptmnet/2023_05_22/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:55.258000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000522/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000522/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c91964c929a81780f454018b741e1764aa2a8e3171a95089a5481146f7ca341f","provenance_domain":{"name":"Human Glycation Sites (UniProtKB)","version":"v-0.0.0","created":"2020-08-17T17:02:18.395740","modified":"2024-12-10T20:04:27.971Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycation Sites (UniProtKB) dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions with information on reported and predicted glycation sites from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"keywords":["UniProtKB","PubMed","Evidence and conculsion Ontology","glycation","reported glycation","predicted glycation","glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycation_sites_uniprotkb.csv","filename":"human_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"make-proteoform-dataset.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":354,"last_update":"2024-12-10T20:04:27.971700Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000522/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000522/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Glycation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-08-17T17:02:18.395740","modified":"2022-09-26T09:08:12.678675","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"74b17d20961758d9ac2f3b52c13cc21a379cebdfc8f1816a280aabf87833de96","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycation_sites_uniprotkb.csv","filename":"human_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.606000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000522/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000522/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Glycation Sites (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-17T17:02:18.395740","modified":"2022-09-26T09:08:12.678675","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"5927e17664a9b14fed4930b36c3bee8a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycation_sites_uniprotkb.csv","filename":"human_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:55.444000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000523/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000523/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cbb384eb0bf3ab0648d75205e1b89bb7bd714d9aab43fefe7e890d4b3f1c4320","provenance_domain":{"name":"Mouse Glycation Sites (UniProtKB)","version":"v-0.0.0","created":"2020-08-17T17:46:24.854615","modified":"2024-12-10T20:08:15.066Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycation Sites (UniProtKB) dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycation sites from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"keywords":["UniProtKB","PubMed","Evidence and conclusion Ontology","glycation","reported glycation ","predicted glycation ","glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":355,"last_update":"2024-12-10T20:08:15.066298Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000523/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000523/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Glycation Sites (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-08-17T17:46:24.854615","modified":"2022-09-26T09:08:12.693077","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"1eb79f9806ff9e44f2f1fd2d80e689158131e971bc31a62eb238d7067e3ab9fd","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.346000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000523/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000523/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Glycation Sites (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-17T17:46:24.854615","modified":"2022-09-26T09:08:12.693077","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"8db6304a9df7f5774facfc1d119b5e43","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:55.625000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000524/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000524/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b2fddea4fe3024d5a4b8fb83d6e5b5c5c0da49c32a1b4146d9da911d0e31dcd7","provenance_domain":{"name":"Rat Glycation Sites (UniProtKB)","version":"v-0.0.0","created":"2020-08-17T17:48:42.126261","modified":"2025-10-09T14:15:45.076Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycation Sites (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2025-10-09T14:15:45.076321Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000524/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000524/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Glycation Sites (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-08-17T17:48:42.126261","modified":"2022-09-26T09:08:12.718203","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Glycation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"971acedcaf34f18989a215bf7207bfce06998485f054ff08855ac9213fe4f89b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.948000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000524/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000524/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Glycation Sites (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-17T17:48:42.126261","modified":"2022-09-26T09:08:12.718203","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["The Rat Glycation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"etag":"8cea9314df945e8906198e12ab35855d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:55.825000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000525/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000525/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease ID Mapping","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Disease ID Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-08-19T14:06:44.941024","modified":"2024-05-17T11:24:03.517Z","version":"v-0.0.0"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Disease Ontology Mapping dataset contains human [taxid:9606] UniProtKB canonical accession cross-reference mappings to the Disease Ontology Ids (DOID)","If you use this dataset please provide proper attribution to GlyGen and Disease ontology, Monarch Disease Ontology and EMBL-EBI-UniProt"],"etag":"474d4efbc2dd435edb70fcbc27d467df0b55248f4edace3f76664d3057f03c6a","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_disease_idmap.csv","filename":"protein_disease_idmap.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_disease_idmap.stat.csv","filename":"protein_disease_idmap.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":295,"last_update":"2024-05-17T11:24:03.517955Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000525/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000525/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease ID Mapping","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Disease ID Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-08-19T14:06:44.941024","modified":"2022-09-26T09:08:12.765026","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Disease Ontology Mapping dataset contains human [taxid:9606] UniProtKB canonical accession cross-reference mappings to the Disease Ontology Ids (DOID)","If you use this dataset please provide proper attribution to GlyGen and Disease ontology, Monarch Disease Ontology and EMBL-EBI-UniProt"],"etag":"b9098a995342e7025a657d9b34e4e7dc9b4eeff1926e0ac4f06704347935f688","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/hcv1a_protein_disease.csv"}},{"uri":{"filename":"hcv1b_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/hcv1b_protein_disease.csv"}},{"uri":{"filename":"sarscov1_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov1_protein_disease.csv"}},{"uri":{"filename":"sarscov2_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov2_protein_disease.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv","filename":"protein_disease_idmap.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.stat.csv","filename":"protein_disease_idmap.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.711000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000525/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000525/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease ID Mapping","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Disease ID Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-19T14:06:44.941024","modified":"2022-09-26T09:08:12.765026","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human Disease Ontology Mapping dataset contains human [taxid:9606] UniProtKB canonical accession cross-reference mappings to the Disease Ontology Ids (DOID)","If you use this dataset please provide proper attribution to GlyGen and Disease ontology, Monarch Disease Ontology and EMBL-EBI-UniProt"],"etag":"80ed74be6d25973e5d4e284f533faae3","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/hcv1a_protein_disease.csv"}},{"uri":{"filename":"hcv1b_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/hcv1b_protein_disease.csv"}},{"uri":{"filename":"sarscov1_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov1_protein_disease.csv"}},{"uri":{"filename":"sarscov2_protein_disease.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov2_protein_disease.csv"}},{"uri":{"filename":"mondo.json","uri":"/data/shared/glyds/downloads/mondo/v2023-04-24/mondo.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv","filename":"protein_disease_idmap.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.stat.csv","filename":"protein_disease_idmap.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:56.020000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000526/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000526/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9d1d7495a55ccea7aa359ace84e2cd765e59bb2fe49c6798ce1075f647dd66a5","provenance_domain":{"name":"Disease Names","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-08-19T14:13:07.626533","modified":"2025-12-16T16:42:33.332Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Disease Name dataset contains the IDs, recommended names, synonyms and descriptions for Diseases in GlyGen from Mondo Disease Ontology (Mondo), OMIM and The Disease Ontology Knowledgebase (DO-KB). If you use this dataset please provide proper attribution to Mondo, OMIM, DO-KB and GlyGen.","The Mondo Disease Ontology (Mondo) aims to harmonize disease definitions across the world by providing a hierarchical structure which can be used for classification or “rolling up” diseases to higher level groupings, and mappings to other disease resources using strict semantics (https://mondo.monarchinitiative.org). ","OMIM is a comprehensive, authoritative compendium of human genes and genetic phenotypes (https://www.omim.org).","The Disease Ontology Knowledgebase (DO-KB) provides access for exploring integrated disease mechanism and feature knowledge, semantically-defined within the Human Disease Ontology (https://disease-ontology.org)."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_disease_names.csv","filename":"protein_disease_names.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_disease_names.stat.csv","filename":"protein_disease_names.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1124,"last_update":"2025-12-16T16:42:33.332063Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000526/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000526/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Disease Names","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-08-19T14:13:07.626533","modified":"2022-09-26T09:08:12.449304","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["",""],"etag":"db445aa0a2e4448b576124238abf4d7d961554099c86a2e08f82381b9f4afedc","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_names.csv","filename":"protein_disease_names.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_names.stat.csv","filename":"protein_disease_names.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.342000Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000526/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000526/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Disease Names","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-08-19T14:13:07.626533","modified":"2022-09-26T09:08:12.449304","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["",""],"etag":"dde9b730337922f8bd0bcbd50cde5b6c","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}},{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_names.csv","filename":"protein_disease_names.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_names.stat.csv","filename":"protein_disease_names.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:56.221000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000527/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000527/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"77c5f5588ff437b225e8abe2db25dca668267753183adf43adabec579c930522","provenance_domain":{"name":"Sandbox accessions (GlyTouCan Accession)","version":"v-0.0.0","created":"2020-09-10T15:28:11.224030","modified":"2024-05-17T11:24:03.592Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"University of Georgia","contribution":["authoredBy","contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset includes GlyTouCan accessions included in Sandbox application."],"description_domain":{"keywords":["GlyTouCan accessions","Glycans","Sandbox"],"platform":[],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The dataset was directly downloaded from the provider and a script was used to check if the GlyTouCan Ac is included in the glycan masterlist (https://data.glygen.org/GLY_000281)"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_sandbox.csv","filename":"glycan_xref_sandbox.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_sandbox.stat.csv","filename":"glycan_xref_sandbox.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Sanbox Glycan accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":74,"last_update":"2024-05-17T11:24:03.592144Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000527/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000527/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Sanbox Glycan accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Sandbox accessions (GlyTouCan Accession)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"University of Georgia","contribution":["providedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-09-10T15:28:11.224030","modified":"2022-09-26T09:08:12.536494","version":"v-2.0.2"},"description_domain":{"keywords":["GlyTouCan accessions","Glycans","Sandbox"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/sandbox_accessions.csv","filename":"sandbox_accessions.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_sandbox.csv","filename":"glycan_xref_sandbox.csv"}],"prerequisite":[],"description":"The dataset was directly downloaded from the provider and a script was used to check if the GlyTouCan Ac is included in the glycan masterlist (https://data.glygen.org/GLY_000281)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset includes GlyTouCan accessions included in Sandbox application."],"etag":"585e38414d33d4f0ccb95ea106307a43d39992733380e5aa8795d2c0bf4f8401","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"sandbox_accessions.csv","uri":"https:/data.glygen.org/ln2downloads/sandbox/02_06_2022/sandbox_accessions.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_sandbox.csv","filename":"glycan_xref_sandbox.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_sandbox.stat.csv","filename":"glycan_xref_sandbox.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.670000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000527/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000527/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"752d9de024f7808bdfeb88437bec88b3","provenance_domain":{"name":"Sandbox accessions (GlyTouCan Accession)","version":"v-2.1.1","created":"2020-09-10T15:28:11.224030","modified":"2023-02-15T19:12:32.564Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"University of Georgia","contribution":["authoredBy","contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset includes GlyTouCan accessions included in Sandbox application."],"description_domain":{"keywords":["GlyTouCan accessions","Glycans","Sandbox"],"platform":[],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/sandbox_accessions.csv","filename":"sandbox_accessions.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_sandbox.csv","filename":"glycan_xref_sandbox.csv"}],"prerequisite":[],"description":"The dataset was directly downloaded from the provider and a script was used to check if the GlyTouCan Ac is included in the glycan masterlist (https://data.glygen.org/GLY_000281)"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"accessionlist.csv","uri":"/data/shared/glyds/downloads/sandbox/05_17_2023/accessionlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_sandbox.csv","filename":"glycan_xref_sandbox.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_sandbox.stat.csv","filename":"glycan_xref_sandbox.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Sanbox Glycan accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:56.418000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000529/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000529/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease GlyCosmos","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Protein Diseases (GlyCosmos)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-09-24T13:34:03.947890","modified":"2024-05-17T11:24:03.629Z","version":"v-0.0.0"},"description_domain":{"keywords":["Gene","Protein","Disease","GlyCosmos"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The file is downloaded from the GlyCosmos database directly. The following steps are done to generate the final output file: 1. Mapping gene_id to UniProtKB accession from input file 1 2) Map the dd_uri to mim_id and disease name from input file 2 3) Map mim_id to doid and mongo ids using input file 3. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The file contain disease data associated to protein/gene downloaded from GlyCosmos database. [https://glycosmos.org/homes/download]. "],"etag":"ddeed64e4df4a5d2c24adfb8d55a7e1172ddf03b70e373e23e4aad7f202b165a","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_glycosmos.csv","filename":"human_protein_disease_glycosmos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_disease_glycosmos.stat.csv","filename":"human_protein_disease_glycosmos.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":133,"last_update":"2024-05-17T11:24:03.629192Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000529/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000529/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease GlyCosmos","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Protein Diseases (GlyCosmos)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2020-09-24T13:34:03.947890","modified":"2022-09-26T09:08:12.748887","version":"v-2.0.2"},"description_domain":{"keywords":["Gene","Protein","Disease","GlyCosmos"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/source/ggdonto.ttl","filename":"ggdonto.ttl"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/source/protein_disease_idmap.csv","filename":"protein_disease_idmap.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/ human_protein_disease_glycosmos.csv","filename":" human_protein_disease_glycosmos.csv"}],"prerequisite":[],"description":"The file is downloaded from the GlyCosmos database directly. The following steps are done to generate the final output file: 1. Mapping gene_id to UniProtKB accession from input file 1 2) Map the dd_uri to mim_id and disease name from input file 2 3) Map mim_id to doid and mongo ids using input file 3. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The file contain disease data associated to protein/gene downloaded from GlyCosmos database. [https://glycosmos.org/homes/download]. "],"etag":"a4dffa8939148ea911165cffb53dd9836c0650ddce790abff6bbf60ea3889800","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"glycosmos_gdgdb.csv","uri":"https:/data.glygen.org/ln2downloads/glycosmos/04_08_2021/glycosmos_gdgdb.csv"}},{"uri":{"filename":"ggdonto.ttl","uri":"https:/data.glygen.org/ln2downloads/glycosmos/04_08_2021/graph-1/ggdonto.ttl"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_glycosmos.csv","filename":"human_protein_disease_glycosmos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_disease_glycosmos.stat.csv","filename":"human_protein_disease_glycosmos.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.521000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000529/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000529/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease GlyCosmos","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Protein Diseases (GlyCosmos)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-09-24T13:34:03.947890","modified":"2022-09-26T09:08:12.748887","version":"v-2.1.1"},"description_domain":{"keywords":["Gene","Protein","Disease","GlyCosmos"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/source/ggdonto.ttl","filename":"ggdonto.ttl"},{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/source/protein_disease_idmap.csv","filename":"protein_disease_idmap.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/ human_protein_disease_glycosmos.csv","filename":" human_protein_disease_glycosmos.csv"}],"prerequisite":[],"description":"The file is downloaded from the GlyCosmos database directly. The following steps are done to generate the final output file: 1. Mapping gene_id to UniProtKB accession from input file 1 2) Map the dd_uri to mim_id and disease name from input file 2 3) Map mim_id to doid and mongo ids using input file 3. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The file contain disease data associated to protein/gene downloaded from GlyCosmos database. [https://glycosmos.org/homes/download]. "],"etag":"9a29396276e95bfe1981371413088d66","io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"glycosmos_gdgdb.csv","uri":"/data/shared/glyds/downloads/glycosmos/04_08_2021/glycosmos_gdgdb.csv"}},{"uri":{"filename":"ggdonto.ttl","uri":"/data/shared/glyds/downloads/glycosmos/04_08_2021/graph-1/ggdonto.ttl"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_glycosmos.csv","filename":"human_protein_disease_glycosmos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_disease_glycosmos.stat.csv","filename":"human_protein_disease_glycosmos.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:56.612000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000530/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000530/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Glycosylation sites","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2020-09-24T13:36:00.724463","modified":"2024-05-17T11:24:03.671Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in UniProtKB for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (sarscov2_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS-CoV2 Glycosylation Sites (GlyConnect) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Severe acute respiratory syndrome coronavirus 2 (2019-nCoV)). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"57dfeb6892a1f2a009c6f04aba0a0d6445679eb61c7531ca2a91af79df2f2e7a","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":610,"last_update":"2024-05-17T11:24:03.671198Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000530/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000530/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Glycosylation sites","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-09-24T13:36:00.724463","modified":"2022-09-26T09:08:12.455012","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glyconnect_sarscov2.json","filename":"glyconnect_sarscov2.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/sarscov2_proteoform_glycosylation_sites_glyconnect.1.log","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (sarscov2_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS-CoV2 Glycosylation Sites (GlyConnect) dataset contains SARS-CoV2 [taxid:2697049] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Severe acute respiratory syndrome coronavirus 2 (2019-nCoV)). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"72562dd100aa80fb2d69849fabd7e25dc9e80dfadfa7bfde6002026ce607a614","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"glyconnect_sarscov2.json","uri":"https:/data.glygen.org/ln2downloads/glyconnect/2022_03_14/glyconnect_sarscov2.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.971000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000530/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000530/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Glycosylation sites","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2020-09-24T13:36:00.724463","modified":"2022-09-26T09:08:12.455012","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glyconnect_sarscov2.json","filename":"glyconnect_sarscov2.json"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/sarscov2_proteoform_glycosylation_sites_glyconnect.1.log","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.1.log"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (sarscov2_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS-CoV2 Glycosylation Sites (GlyConnect) dataset contains SARS-CoV2 [taxid:2697049] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Severe acute respiratory syndrome coronavirus 2 (2019-nCoV)). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"etag":"21bea90230d9c8370901f99ffcb69128","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"glycosylations?taxonomy=Severe acute respiratory syndrome coronavirus 2 (2019-nCoV)","uri":"/data/shared/glyds/downloads/glyconnect/2023_05_18/glycosylations?taxonomy=Severe acute respiratory syndrome coronavirus 2 (2019-nCoV)"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:56.803000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000535/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000535/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cdb8c7af5c71ce891f2b70a0bd4e16fb30edda4cba5735262538c1fc05a84f68","provenance_domain":{"name":"SARS-CoV2 Proteoform Citations (GlyConnect)","version":"v-0.0.0","created":"2020-12-11T14:19:01.972822","modified":"2024-05-17T11:24:03.709Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":""},"usability_domain":["The SARS-CoV2 Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000530. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":444,"last_update":"2024-05-17T11:24:03.709718Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000535/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000535/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Proteoform Citations (GlyConnect)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2020-12-11T14:19:01.972822","modified":"2022-09-26T09:08:12.696068","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_glyconnect.csv","filename":"sarscov2_proteoform_citations_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS-CoV2 Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000530. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"etag":"e4ecb1ab9f0da1a7874e9cde65fd4b4d85244f37c72813f94426f9ccdf4ecc48","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_proteoform_citations_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov2_proteoform_citations_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_glyconnect.csv","filename":"sarscov2_proteoform_citations_glycosylation_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_glyconnect.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.221000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000535/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000535/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ea6a059c378f1e2e72538e5dce0b0b13","provenance_domain":{"name":"SARS-CoV2 Proteoform Citations (GlyConnect)","version":"v-2.1.1","created":"2020-12-11T14:19:01.972822","modified":"2023-03-14T16:49:58.339Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":["The SARS-CoV2 Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000530. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_proteoform_citations_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov2_proteoform_citations_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:57Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000536/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000536/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Mouse]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-01-04T11:37:44.928218","modified":"2024-05-21T15:27:27.205Z","version":"v-0.0.0"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for mouse [taxid:10090] proteins (https://data.glygen.org/GLY_000041: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB mouse glycoprotein dataset (https://data.glygen.org/GLY_000041: v-1.4.5 09/13/2019)"],"etag":"346eafe75dc2208cec2c09d59f4eaf7e48b7128637df5a8bbdd36d58ae734072","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_pro_annotation.csv","filename":"mouse_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_pro_annotation.stat.csv","filename":"mouse_protein_pro_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":602,"last_update":"2024-05-21T15:27:27.205642Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000536/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000536/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Mouse]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-01-04T11:37:44.928218","modified":"2022-09-26T09:08:12.583203","version":"v-2.0.2"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_pro_annotation.csv","filename":"mouse_protein_pro_annotation.csv"}],"prerequisite":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for mouse [taxid:10090] proteins (https://data.glygen.org/GLYDS000041: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB mouse glycoprotein dataset (https://data.glygen.org/GLYDS000041: v-1.4.5 09/13/2019)"],"etag":"1983a48fd5757f9ae5024e7788fccad3d7816cfd081b43f2506fdde3d517ca50","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"https:/data.glygen.org/ln2downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_pro_annotation.csv","filename":"mouse_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_pro_annotation.stat.csv","filename":"mouse_protein_pro_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.112000Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000536/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000536/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Mouse]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-01-04T11:37:44.928218","modified":"2022-09-26T09:08:12.583203","version":"v-2.1.1"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_pro_annotation.csv","filename":"mouse_protein_pro_annotation.csv"}],"prerequisite":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for mouse [taxid:10090] proteins (https://data.glygen.org/GLYDS000041: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB mouse glycoprotein dataset (https://data.glygen.org/GLYDS000041: v-1.4.5 09/13/2019)"],"etag":"ae1ac4a5b88d391d4d755ee14e931541","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"/data/shared/glyds/downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_pro_annotation.csv","filename":"mouse_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_pro_annotation.stat.csv","filename":"mouse_protein_pro_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:57.194000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000537/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000537/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Rat]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-01-04T11:52:52.688289","modified":"2024-05-21T15:28:12.013Z","version":"v-0.0.0"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for rat [taxid:10116] proteins (https://data.glygen.org/GLY_000221: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB rat glycoprotein dataset (https://data.glygen.org/GLY_000221: v-1.4.5 09/13/2019)"],"etag":"8a419bc1f635db366fb6d2a9984e59ed5194368fd3df4f183fbb31ab33c27709","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_pro_annotation.csv","filename":"rat_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_pro_annotation.stat.csv","filename":"rat_protein_pro_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":598,"last_update":"2024-05-21T15:28:12.013234Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000537/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000537/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Rat]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-01-04T11:52:52.688289","modified":"2022-09-26T09:08:12.584483","version":"v-2.0.2"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_pro_annotation.csv","filename":"rat_protein_pro_annotation.csv"}],"prerequisite":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for rat [taxid:10116] proteins (https://data.glygen.org/GLYDS000221: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB rat glycoprotein dataset (https://data.glygen.org/GLYDS000221: v-1.4.5 09/13/2019)"],"etag":"f8201881f40572e19b0dc85fd310976e1b0cf7383a872908edbc669b5ec57164","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"https:/data.glygen.org/ln2downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_pro_annotation.csv","filename":"rat_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_pro_annotation.stat.csv","filename":"rat_protein_pro_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.012000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000537/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000537/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Rat]","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-01-04T11:52:52.688289","modified":"2022-09-26T09:08:12.584483","version":"v-2.1.1"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_pro_annotation.csv","filename":"rat_protein_pro_annotation.csv"}],"prerequisite":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for rat [taxid:10116] proteins (https://data.glygen.org/GLYDS000221: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB rat glycoprotein dataset (https://data.glygen.org/GLYDS000221: v-1.4.5 09/13/2019)"],"etag":"cba815f9431665ea1f4e908abbf95f08","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"/data/shared/glyds/downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_pro_annotation.csv","filename":"rat_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_pro_annotation.stat.csv","filename":"rat_protein_pro_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:57.394000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000538/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000538/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d628e3af1a5f44ec4ec20ad31bba36e3ed372bf937c8e0ccafd64061f7ccfec4","provenance_domain":{"name":"Glycan Citations (NCFG)","version":"v-0.0.0","created":"2021-01-04T15:07:01.965445","modified":"2024-05-17T11:24:03.825Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Richard Cummings","contribution":["contributedBy"],"affiliation":"Harvard Medical School","email":"rcummin1@bidmc.harvard.edu","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Glycan Citations (NCFG) dataset contains publication information for a library of complex multiantennary Asn-linked N-glycans generated by chemo-enzymatic synthesis, including PMID, journal name, date, author and title. The dataset is derived from the dataset contributed by the Richard Cummings Laboratory (NCFG BIDMC Harvard Medical School) http://data.glygen.org/GLY_000600."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations","NCFG"],"platform":[],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_ncfg.stat.csv","filename":"glycan_citations_ncfg.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":381,"last_update":"2024-05-17T11:24:03.825692Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000538/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000538/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Asparagine-Linked Glycans (PMID30745240) [NCFG]  citations.","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-01-04T15:07:01.965445","modified":"2022-09-26T09:08:12.653000","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations","NCFG"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_evidence_ncfg.csv","filename":"glycan_evidence_ncfg.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from dataset http://data.glygen.org/GLY_000528. "],"etag":"4e13af1418652b7c2374582f28fa4421564ce23c7d29ba0d3f78b3a71f6afaa1","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_evidence_ncfg.csv","uri":"https:/data.glygen.org/ln2downloads/ncfg/09_01_2020/glycan_evidence_ncfg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_ncfg.stat.csv","filename":"glycan_citations_ncfg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.809000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000538/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000538/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3b956b30e3a7e8859fbffebe0eceeecc","provenance_domain":{"name":"Glycan Citations (NCFG)","version":"v-2.1.1","created":"2021-01-04T15:07:01.965445","modified":"2023-03-07T02:00:44.381Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Richard Cummings","contribution":["contributedBy"],"affiliation":"Harvard Medical School","email":"rcummin1@bidmc.harvard.edu","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Glycan Citations (NCFG) dataset contains publication information for a library of complex multiantennary Asn-linked N-glycans generated by chemo-enzymatic synthesis, including PMID, journal name, date, author and title. The dataset is derived from the dataset contributed by the Richard Cummings Laboratory (NCFG BIDMC Harvard Medical School) http://data.glygen.org/GLY_000600."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations","NCFG"],"platform":[],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_evidence_ncfg.csv","filename":"glycan_evidence_ncfg.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_evidence_ncfg.csv","uri":"/data/shared/glyds/downloads/ncfg/09_01_2020/glycan_evidence_ncfg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_ncfg.stat.csv","filename":"glycan_citations_ncfg.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:57.592000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000539/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000539/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GNOme","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GNOme","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-02-11T14:43:28.543150","modified":"2024-05-17T11:24:03.864Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GNOme","accessions","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The datasets provides a list of GlyTouCan accessions which are supported by GNOme ontology (https://gnome.glyomics.org/) (https://gnome.glyomics.org/restrictions/GlyGen.StructureBrowser.html). "],"etag":"787919ed4c145fd3c0567fea4782f5a41676e85c9ec6846eb3f4fa83c13e7fbd","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_gnome.csv","filename":"glycan_xref_gnome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_gnome.stat.csv","filename":"glycan_xref_gnome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":193,"last_update":"2024-05-17T11:24:03.864787Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000539/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000539/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GNOme","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GNOme","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-11T14:43:28.543150","modified":"2022-09-26T09:08:12.713090","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GNOme","accessions","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/gnome.tsv","filename":"gnome.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_gnome.csv","filename":"glycan_xref_gnome.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The datasets provides a list of GlyTouCan accessions which are supported by GNOme ontology (https://gnome.glyomics.org/) (https://gnome.glyomics.org/restrictions/GlyGen.StructureBrowser.html). "],"etag":"ccf4ff2b7ee63ce0f77dd22542d31a69b391cf0f30535583785dbc21eb9752f9","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"gnome.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/gnome.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_gnome.csv","filename":"glycan_xref_gnome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_gnome.stat.csv","filename":"glycan_xref_gnome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.031000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000539/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000539/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GNOme","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GNOme","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-11T14:43:28.543150","modified":"2022-09-26T09:08:12.713090","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GNOme","accessions","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/gnome.tsv","filename":"gnome.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_gnome.csv","filename":"glycan_xref_gnome.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The datasets provides a list of GlyTouCan accessions which are supported by GNOme ontology (https://gnome.glyomics.org/) (https://gnome.glyomics.org/restrictions/GlyGen.StructureBrowser.html). "],"etag":"230d1077fdb9d08a981577758f437bb4","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"gnome.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/gnome.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_gnome.csv","filename":"glycan_xref_gnome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_gnome.stat.csv","filename":"glycan_xref_gnome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:57.789000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000540/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000540/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"36c856836fa600b2066bdddcb8c32915f5d348c95cb245036122b72235583128","provenance_domain":{"name":"NCBI Gene Linkouts","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T17:05:56.978751","modified":"2025-07-31T11:52:55.866Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The NCBI Gene Linkouts dataset contains NCBI Gene IDs with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into three files."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_ncbi_gene_linkouts_one.csv","filename":"protein_ncbi_gene_linkouts_one.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_ncbi_gene_linkouts_one.stat.csv","filename":"protein_ncbi_gene_linkouts_one.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkout","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae S288C"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H77)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Gallus gallus"},{"category_name":"species","category_value":"Bos taurus"},{"category_name":"species","category_value":"Cricetulus griseus"},{"category_name":"species","category_value":"Danio rerio"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":371,"last_update":"2025-07-31T11:52:55.866963Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000540/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000540/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"NCBI Gene Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-02-22T17:05:56.978751","modified":"2022-01-20T16:09:07.330286","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"8a6384f9839f3337388281f7ac4446d1","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_geneid.csv"}},{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"mouse_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_geneid.csv"}},{"uri":{"filename":"rat_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_geneid.csv"}},{"uri":{"filename":"sarscov1_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_geneid.csv"}},{"uri":{"filename":"sarscov2_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_geneid.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_gene_linkouts.csv","filename":"protein_ncbi_gene_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_gene_linkouts.stat.csv","filename":"protein_ncbi_gene_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.613000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000540/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000540/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"NCBI Gene Linkouts","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T17:05:56.978751","modified":"2022-01-20T16:09:07.330286","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"86a60ab5dfa8a797b80ab25740d88006","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_geneid.csv"}},{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"mouse_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv"}},{"uri":{"filename":"rat_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_geneid.csv"}},{"uri":{"filename":"sarscov1_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_geneid.csv"}},{"uri":{"filename":"sarscov2_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_geneid.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_gene_linkouts.csv","filename":"protein_ncbi_gene_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_gene_linkouts.stat.csv","filename":"protein_ncbi_gene_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:58.129000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000541/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000541/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref NCBI Gene","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T17:20:29.683156","modified":"2024-06-03T21:23:52.092Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref NCBI Gene dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"589adbee60172113f25c78bce84f12ec20ca1678672de23b07123c654f737aec","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_geneid.csv","filename":"sarscov2_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_geneid.stat.csv","filename":"sarscov2_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":580,"last_update":"2024-06-03T21:23:52.092047Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000541/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000541/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 UniProtKB Xref NCBI Gene","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T17:20:29.683156","modified":"2022-09-26T09:08:12.544394","version":"v-2.0.2"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarcov2_protein_masterlist.csv","filename":"sarcov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarcov2_protein_xref_geneid.csv","filename":"sarcov2_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref NCBI Gene dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"ae99467356a20fc864f5b7f37a6e3d1cc7b732e63722f3aa7689c04ebdc5e1ec","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_geneid.csv","filename":"sarscov2_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_geneid.stat.csv","filename":"sarscov2_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.163000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000541/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000541/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref NCBI Gene","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T17:20:29.683156","modified":"2022-09-26T09:08:12.544394","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["curatedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarcov2_protein_masterlist.csv","filename":"sarcov2_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-sars-coronavirus.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarcov2_protein_xref_geneid.csv","filename":"sarcov2_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref NCBI Gene dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"etag":"7afd2b069a6807438013a37a844600e0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_geneid.csv","filename":"sarscov2_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_geneid.stat.csv","filename":"sarscov2_protein_xref_geneid.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:58.331000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000542/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000542/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species","category_value":"Hepatitis C virus (isolate Japanese)"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae S288C"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB accessions list","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"UniProtKB Accession History","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T17:29:38.073620","modified":"2024-05-17T11:24:03.984Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["UniProtKB accessions list","replaced"]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The UniProtKB Accession History dataset contains a list of historical UniProtKB accessions mapped to the current accession number. This mapping is used to provide error messages with links to current protein pages on GlyGen."],"etag":"b767b7a1bcf3d72f5cb48753b82435e5f5d9cd2466fcd9c0ced35b58c4d2d3b4","io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_uniprotkb_accession_history.csv","filename":"protein_uniprotkb_accession_history.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_uniprotkb_accession_history.stat.csv","filename":"protein_uniprotkb_accession_history.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":224,"last_update":"2024-05-17T11:24:03.984545Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000542/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000542/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB accessions list","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"UniProtKB accession History","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T17:29:38.073620","modified":"2022-09-26T09:08:12.697965","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB accessions list","replaced"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"bc21a255368ce0ebdf6165f44099837ae718e72d93818ef8a7add355d4c51aad","io_domain":{"input_subdomain":[{"uri":{"filename":"accession-history-drosophila-melanogaster.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-drosophila-melanogaster.tsv"}},{"uri":{"filename":"accession-history-hepatitis-c-virus-1a.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-hepatitis-c-virus-1a.tsv"}},{"uri":{"filename":"accession-history-hepatitis-c-virus-1b.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-hepatitis-c-virus-1b.tsv"}},{"uri":{"filename":"accession-history-homo-sapiens.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-homo-sapiens.tsv"}},{"uri":{"filename":"accession-history-mus-musculus.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-mus-musculus.tsv"}},{"uri":{"filename":"accession-history-rattus-norvegicus.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-rattus-norvegicus.tsv"}},{"uri":{"filename":"accession-history-sars-coronavirus.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-sars-coronavirus.tsv"}},{"uri":{"filename":"accession-history-sars-cov-2.tsv","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/accession-history-sars-cov-2.tsv"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_uniprotkb_accession_history.csv","filename":"protein_uniprotkb_accession_history.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_uniprotkb_accession_history.stat.csv","filename":"protein_uniprotkb_accession_history.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.516000Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000542/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000542/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB accessions list","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Hepatitis C virus (genotype 1a, isolate H)"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"UniProtKB accession History","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T17:29:38.073620","modified":"2023-09-11T23:04:06","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB accessions list","replaced"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"a05b0c90b1380a069455b719558d9fdabff37cb8","io_domain":{"input_subdomain":[{"uri":{"filename":"accession-history-dictyostelium_discoideum.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-dictyostelium_discoideum.tsv"}},{"uri":{"filename":"accession-history-drosophila-melanogaster.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-drosophila-melanogaster.tsv"}},{"uri":{"filename":"accession-history-hepatitis-c-virus-1a.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-hepatitis-c-virus-1a.tsv"}},{"uri":{"filename":"accession-history-hepatitis-c-virus-1b.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-hepatitis-c-virus-1b.tsv"}},{"uri":{"filename":"accession-history-homo-sapiens.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-homo-sapiens.tsv"}},{"uri":{"filename":"accession-history-mus-musculus.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-mus-musculus.tsv"}},{"uri":{"filename":"accession-history-rattus-norvegicus.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-rattus-norvegicus.tsv"}},{"uri":{"filename":"accession-history-saccharomyces-cerevisiae.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-saccharomyces-cerevisiae.tsv"}},{"uri":{"filename":"accession-history-sars-coronavirus.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-sars-coronavirus.tsv"}},{"uri":{"filename":"accession-history-sars-cov-2.tsv","uri":"/data/shared/glyds/downloads/ebi/2023_02/accession-history-sars-cov-2.tsv"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_uniprotkb_accession_history.csv","filename":"protein_uniprotkb_accession_history.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_uniprotkb_accession_history.stat.csv","filename":"protein_uniprotkb_accession_history.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-09-11T23:04:13.996000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000543/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000543/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"85425d3e9f65ce38bdff5047610bd73b9a160fbfd4b680c37242c4ee835bcf26","provenance_domain":{"name":"Mouse Protein Diseases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:03:11.844436","modified":"2024-07-09T11:59:26.523Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Protein Diseases contains diseases associated with the Mus musculus [taxid:10090] protein UniProtKB canonical accessions. The dataset also contains mapping of UniProtKB canonical accessions to the Disease Ontology (DO), Mondo and OMIM resources. If you use this dataset please provide proper attribution to GlyGen and Alliance of Genome Resources."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_disease_alliance_genome.csv","filename":"mouse_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_disease_alliance_genome.stat.csv","filename":"mouse_protein_disease_alliance_genome.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-07-09T11:59:26.523511Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000543/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000543/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:03:11.844436","modified":"2022-09-26T09:08:12.672340","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"3209fb120519a0f2c1a66d4d37e1acf7e0d7a6665a976a2ad4ed4a1eeae3071f","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_mgi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_mgi.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"mouse_disease_genome_alliance.csv","uri":"https:/data.glygen.org/ln2downloads/alliance_genome/2021_01/mouse_disease_genome_alliance.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_disease_alliance_genome.csv","filename":"mouse_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_disease_alliance_genome.stat.csv","filename":"mouse_protein_disease_alliance_genome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.893000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000543/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000543/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:03:11.844436","modified":"2022-09-26T09:08:12.672340","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"85bec75e3e10d4fa1f8163fc5f0c4d66","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_mgi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_mgi.csv"}},{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"mouse_disease_genome_alliance.csv","uri":"/data/shared/glyds/downloads/alliance_genome/2021_01/mouse_disease_genome_alliance.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_disease_alliance_genome.csv","filename":"mouse_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_disease_alliance_genome.stat.csv","filename":"mouse_protein_disease_alliance_genome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:58.720000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000544/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000544/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0dd48b23d1923632dfadfa375df36c28bc3009914ad34a2080beae8d7dc71d8e","provenance_domain":{"name":"Rat Protein Diseases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:05:37.789475","modified":"2024-07-09T16:49:54.502Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Protein Diseases contains diseases associated with the Rattus norvegicus [taxid:10116] protein UniProtKB canonical accessions. The dataset also contains mapping of UniProtKB canonical accessions to the Disease Ontology (DO), Mondo and OMIM resources. If you use this dataset please provide proper attribution to GlyGen and Alliance of Genome Resources."],"description_domain":{"keywords":["disease","rat","mim","do","mondo"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_disease_alliance_genome.csv","filename":"rat_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_disease_alliance_genome.stat.csv","filename":"rat_protein_disease_alliance_genome.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2024-07-09T16:49:54.502394Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000544/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000544/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:05:37.789475","modified":"2022-09-26T09:08:12.742728","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"e81460fa6e06d3b0695e98a742224dddcb6853d28eff5489faf13924580293bc","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"rat_protein_xref_rgd.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_rgd.csv"}},{"uri":{"filename":"rat_disease_genome_alliance.csv","uri":"https:/data.glygen.org/ln2downloads/alliance_genome/2021_01/rat_disease_genome_alliance.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_disease_alliance_genome.csv","filename":"rat_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_disease_alliance_genome.stat.csv","filename":"rat_protein_disease_alliance_genome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.603000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000544/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000544/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Diseases","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:05:37.789475","modified":"2022-09-26T09:08:12.742728","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"5badf0446da6a7ccc1acf2e21562cd36","io_domain":{"input_subdomain":[{"uri":{"filename":"protein_disease_idmap.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_disease_idmap.csv"}},{"uri":{"filename":"rat_protein_xref_rgd.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_rgd.csv"}},{"uri":{"filename":"rat_disease_genome_alliance.csv","uri":"/data/shared/glyds/downloads/alliance_genome/2021_01/rat_disease_genome_alliance.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_disease_alliance_genome.csv","filename":"rat_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_disease_alliance_genome.stat.csv","filename":"rat_protein_disease_alliance_genome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:58.910000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000545/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000545/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Human UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:13:44.152483","modified":"2024-05-21T14:37:26.790Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The Human UniProtKB Xref (UniProtKB) dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"7a7dd4786dcc67e5b8ca4dab3a97523df55304fa6b34ff42323aa4312a322221","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_uniprotkb.csv","filename":"human_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_uniprotkb.stat.csv","filename":"human_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":254,"last_update":"2024-05-21T14:37:26.790572Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000545/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000545/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:13:44.152483","modified":"2022-09-26T09:08:12.739579","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"55bbf2a201feaf5cac055b9b3ad5ec210a1c1b55fcea54ffb8cc1c28aac3f1ce","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_uniprotkb.csv","filename":"human_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_uniprotkb.stat.csv","filename":"human_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.241000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000545/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000545/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:13:44.152483","modified":"2022-09-26T09:08:12.739579","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"1e737449c3d63bf249e468e110044940","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_uniprotkb.csv","filename":"human_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_uniprotkb.stat.csv","filename":"human_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:59.096000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000546/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000546/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Mouse UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:16:19.328689","modified":"2024-05-21T14:37:52.316Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse UniProtKB Xref (UniProtKB) dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"59849454cfa1b94267531b2e1042300dd450fd36331ab6d732317e108e707984","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_uniprotkb.csv","filename":"mouse_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_uniprotkb.stat.csv","filename":"mouse_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":255,"last_update":"2024-05-21T14:37:52.316865Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000546/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000546/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:16:19.328689","modified":"2022-09-26T09:08:12.527419","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"92c350963022185018b532f98f57300a7e5d93afa553814982504bccca409988","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_uniprotkb.csv","filename":"mouse_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_uniprotkb.stat.csv","filename":"mouse_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.376000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000546/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000546/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:16:19.328689","modified":"2022-09-26T09:08:12.527419","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"382e9fbf2296170404f8ea61828a59dc","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_uniprotkb.csv","filename":"mouse_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_uniprotkb.stat.csv","filename":"mouse_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:59.291000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000547/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000547/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Rat UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:21:43.992764","modified":"2024-05-21T14:38:13.204Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The Rat UniProtKB Xref (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"bd2d64470a5a961b8b525cd7d837e675770f358feeff91c6fa8fdf3c04d7976f","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_uniprotkb.csv","filename":"rat_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_uniprotkb.stat.csv","filename":"rat_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":258,"last_update":"2024-05-21T14:38:13.204420Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000547/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000547/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:21:43.992764","modified":"2022-09-26T09:08:12.459207","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"8858787b838632e06721edb34a195b47b6d81f1ca23b0a5b94b9b84d0324fe27","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_uniprotkb.csv","filename":"rat_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_uniprotkb.stat.csv","filename":"rat_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.631000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000547/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000547/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:21:43.992764","modified":"2022-09-26T09:08:12.459207","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"2eb4d76623e0c8d6cf31a9408d0ddd35","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_uniprotkb.csv","filename":"rat_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_uniprotkb.stat.csv","filename":"rat_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:59.482000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000548/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000548/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"HCV1a UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:24:34.672161","modified":"2024-05-22T14:44:05.960Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1a UniProtKB Xref (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"c66bdc96566ad0af859e370a7460b6e0a9a290c3b85bb463c4c025076c1b7086","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_uniprotkb.csv","filename":"hcv1a_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_xref_uniprotkb.stat.csv","filename":"hcv1a_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":274,"last_update":"2024-05-22T14:44:05.960695Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000548/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000548/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:24:34.672161","modified":"2022-09-26T09:08:12.755200","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"b881b5da8a92bf41b62c70c592578f778f702e704a6f6039673e298eba188278","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_uniprotkb.csv","filename":"hcv1a_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_xref_uniprotkb.stat.csv","filename":"hcv1a_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.858000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000548/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000548/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:24:34.672161","modified":"2022-09-26T09:08:12.755200","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"7a0dc2140b3638532e496bff70e260dc","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1a.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_uniprotkb.csv","filename":"hcv1a_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_xref_uniprotkb.stat.csv","filename":"hcv1a_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:59.674000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000549/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000549/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"HCV1b UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:28:16.767695","modified":"2024-05-21T14:39:36.509Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The HCV1b UniProtKB Xref (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"4b37498582dc3985ebb57b5e1b68b92cd6217f47b8c66ccf48c4dd8f59ccf20f","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_uniprotkb.csv","filename":"hcv1b_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_protein_xref_uniprotkb.stat.csv","filename":"hcv1b_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":279,"last_update":"2024-05-21T14:39:36.509688Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000549/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000549/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:28:16.767695","modified":"2022-09-26T09:08:12.729552","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"4feab30c04f6df03c6cb535f9d9de7ac729a6f86424f39dd4feab4ab5ce7320b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_uniprotkb.csv","filename":"hcv1b_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_xref_uniprotkb.stat.csv","filename":"hcv1b_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.747000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000549/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000549/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:28:16.767695","modified":"2022-09-26T09:08:12.729552","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"a7a604320a0f4d01fa5befe7981f80dc","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-hepatitis-c-virus-1b.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_uniprotkb.csv","filename":"hcv1b_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_xref_uniprotkb.stat.csv","filename":"hcv1b_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:54:59.861000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000550/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000550/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:30:52.415165","modified":"2024-05-21T14:40:02.723Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["The SARS-CoV1 UniProtKB Xref (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"etag":"3131caeb43ea6bce1ee730bfaa8985d6f30f9340d6d05f13db1bafaff44df557","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_uniprotkb.csv","filename":"sarscov1_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_xref_uniprotkb.stat.csv","filename":"sarscov1_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-05-21T14:40:02.723355Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000550/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000550/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:30:52.415165","modified":"2022-09-26T09:08:12.498195","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"f1ec027792aa6fe536f373000340b9da1e0101fab3297c81eedff6cdcb2ed416","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_uniprotkb.csv","filename":"sarscov1_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_uniprotkb.stat.csv","filename":"sarscov1_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:30.528000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000550/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000550/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:30:52.415165","modified":"2022-09-26T09:08:12.498195","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"228b6016573e56486a22aabee03ca820","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-coronavirus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_uniprotkb.csv","filename":"sarscov1_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_uniprotkb.stat.csv","filename":"sarscov1_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:00.049000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000551/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000551/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","usability_domain":["The SARS-CoV2 UniProtKB Xref (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T18:34:38.792491","modified":"2024-05-17T11:24:04.341Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"etag":"e0497dd2eb69e02184649fe77421d91a9110fe1d7d0d89c17c9202aaa8676403","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_uniprotkb.csv","filename":"sarscov2_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_uniprotkb.stat.csv","filename":"sarscov2_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":296,"last_update":"2024-05-17T11:24:04.341001Z","access_count":10},{"object_id":"https://biocomputeobject.org/GLY_000551/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000551/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:34:38.792491","modified":"2022-09-26T09:08:12.466947","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"04ad084c9ed078241b309aa48e1dcae67e3c41c0b30f96b55f7896ebcb285e11","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_uniprotkb.csv","filename":"sarscov2_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_uniprotkb.stat.csv","filename":"sarscov2_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.462000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000551/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000551/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB xref UniProtKB","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:34:38.792491","modified":"2022-09-26T09:08:12.466947","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"f8bfbc7d4e48f15ccaca9e28de2a2248","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_uniprotkb.csv","filename":"sarscov2_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_uniprotkb.stat.csv","filename":"sarscov2_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:00.242000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000552/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000552/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyTouCan","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyTouCan","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-02-22T18:49:04.081640","modified":"2024-05-17T11:24:04.380Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlyTouCan for the for GlyGen Mapper tool. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)"],"etag":"2ee6747826fef9bfc8e27db96188825de57c70529b998d30db01f5d750369097","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glytoucan.csv","filename":"glycan_xref_glytoucan.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glytoucan.stat.csv","filename":"glycan_xref_glytoucan.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":205,"last_update":"2024-05-17T11:24:04.380042Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000552/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000552/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyTouCan","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyTouCan","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T18:49:04.081640","modified":"2022-09-26T09:08:12.746691","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_glytoucan.csv","filename":"glycan_xref_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlyTouCan for the for GlyGen Mapper tool. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)"],"etag":"d94aec3c6a72efa61e1b4de4039b0ca5d1ec9c610886444fa38461cfccf46d95","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glytoucan.csv","filename":"glycan_xref_glytoucan.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glytoucan.stat.csv","filename":"glycan_xref_glytoucan.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.357000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000552/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000552/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyTouCan","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyTouCan","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T18:49:04.081640","modified":"2022-09-26T09:08:12.746691","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_glytoucan.csv","filename":"glycan_xref_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to GlyTouCan for the for GlyGen Mapper tool. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)"],"etag":"4ecbde3f69a9bbee211d68ac0841f8d2","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glytoucan.csv","filename":"glycan_xref_glytoucan.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glytoucan.stat.csv","filename":"glycan_xref_glytoucan.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:00.437000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000553/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000553/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"53b175ddbbf86f88b5c9a4ddb8566228d7e7672c924ad8f58e6607cf38431d24","provenance_domain":{"name":"Human Xref The O-GlcNAc Database","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-02-22T19:23:09.094102","modified":"2024-07-29T19:35:36.765Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Human Xref The O-GlcNAc Database contains human (taxid:9606) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions."}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_oglcnac_mcw.csv","filename":"human_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_oglcnac_mcw.stat.csv","filename":"human_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":139,"last_update":"2024-07-29T19:35:36.765525Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000553/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000553/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Xref The O-GlcNAc Database","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-02-22T19:23:09.094102","modified":"2022-09-26T09:08:12.736098","version":"v-2.0.2"},"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_citations_o_glcnac_mcw.csv","filename":"human_proteoform_citations_o_glcnac_mcw.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["Human Xref The O-GlcNAc Database contains human (taxid:9606) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"etag":"d11400ef85769e7d94a03c1be963013f504d9ce7a27f60b8018b253a527cdbdc","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_oglcnac_db.csv","filename":"human_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_oglcnac_db.stat.csv","filename":"human_protein_xref_oglcnac_db.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.612000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000553/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000553/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Xref The O-GlcNAc Database","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-22T19:23:09.094102","modified":"2022-09-26T09:08:12.736098","version":"v-2.1.1"},"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_o_glcnac_mcw.csv","filename":"human_proteoform_citations_o_glcnac_mcw.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"usability_domain":["Human Xref The O-GlcNAc Database contains human (taxid:9606) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"etag":"0bd4f3465bfd3c254cd97a3a3d25a418","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oglcnac_db.csv","filename":"human_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oglcnac_db.stat.csv","filename":"human_protein_xref_oglcnac_db.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:00.628000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000554/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000554/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-03-01T11:27:34.342151","modified":"2024-05-17T11:24:04.459Z","version":"v-0.0.0"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref NCBI Gene dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"etag":"7ced48a86f839b74462bdbb54ed197840eb2573df68ec1486e7c19faa7d082ff","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_info_refseq.csv","filename":"sarscov2_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_info_refseq.stat.csv","filename":"sarscov2_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":353,"last_update":"2024-05-17T11:24:04.459567Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000554/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000554/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-03-01T11:27:34.342151","modified":"2022-09-26T09:08:12.700740","version":"v-2.0.2"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_info_refseq.csv","filename":"sarscov2_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref NCBI Gene dataset contains sarscov2 [taxid:2697049] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"ec2258f5fabda1ce29f2266ad858a9d49e916d2b7b85805ce79850a6d3dc7c6c","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_viral.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_viral.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_info_refseq.csv","filename":"sarscov2_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_info_refseq.stat.csv","filename":"sarscov2_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.812000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000554/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000554/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Information (NCBI RefSeq)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-03-01T11:27:34.342151","modified":"2022-09-26T09:08:12.700740","version":"v-2.1.1"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_info_refseq.csv","filename":"sarscov2_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref NCBI Gene dataset contains sarscov2 [taxid:2697049] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"9b7b47eedab36ca23be185acddf1b1ca","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_viral.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_viral.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_info_refseq.csv","filename":"sarscov2_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_info_refseq.stat.csv","filename":"sarscov2_protein_info_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:00.824000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000555/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000555/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"glycan","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"UniProtKB ProtVista Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-02-26T12:11:00.289136","modified":"2024-05-17T11:24:04.501Z","version":"v-0.0.0"},"description_domain":{"keywords":["UniProtKB","Glycans","ChEBI ID","ProtVista"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"Glycosylation annotation from input files were combined together. The glytoucan_ac was mapped to chebi_id using another input file. Additionally, two new columns uniprot_ac and tax_id were added in the output file. The following filtering rules wer applied: 1) Only those protein + site were inlcuded which are present in UniProtKB database 2) Only those rows were included where a valid ChEBI ID was present. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The file includes glycan annotation (GlyTouCan ac and ChEBI Id) for the protein + site included in UniProtKB(https://uniprot.org/) database. "],"etag":"b88d2fb4ef87e20ea0c4a16a5b72acf5a4ed553012bb7c3f0beada1e6eef34ba","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv","filename":"protein_glygen_uniprotkb_protvista_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_uniprotkb_protvista_mapping.stat.csv","filename":"protein_glygen_uniprotkb_protvista_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":141,"last_update":"2024-05-17T11:24:04.501463Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000555/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000555/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"glycan","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"UniProtKB ProtVista Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-02-26T12:11:00.289136","modified":"2022-09-26T09:08:12.666119","version":"v-2.0.2"},"description_domain":{"keywords":["UniProtKB","Glycans","ChEBI ID","ProtVista"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":" https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":" hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":" https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":" hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv","filename":"protein_glygen_uniprotkb_protvista_mapping.tsv"}],"prerequisite":[],"description":"Glycosylation annotation from input files were combined together. The glytoucan_ac was mapped to chebi_id using another input file. Additionally, two new columns uniprot_ac and tax_id were added in the output file. The following filtering rules wer applied: 1) Only those protein + site were inlcuded which are present in UniProtKB database 2) Only those rows were included where a valid ChEBI ID was present. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The file includes glycan annotation (GlyTouCan ac and ChEBI Id) for the protein + site included in UniProtKB(https://uniprot.org/) database. "],"etag":"b3a99357eb6e27f8cc23b81774ec51a6aa37ad4a4d1f7c04d0c8ba842a4749cc","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_chebi.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv","filename":"protein_glygen_uniprotkb_protvista_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_protvista_mapping.stat.csv","filename":"protein_glygen_uniprotkb_protvista_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:08.018000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000555/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000555/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"glycan","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"provenance_domain":{"license":"","name":"UniProtKB ProtVista Mapping","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-02-26T12:11:00.289136","modified":"2022-09-26T09:08:12.666119","version":"v-2.1.1"},"description_domain":{"keywords":["UniProtKB","Glycans","ChEBI ID","ProtVista"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":" https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":" hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":" https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":" hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv","filename":"protein_glygen_uniprotkb_protvista_mapping.tsv"}],"prerequisite":[],"description":"Glycosylation annotation from input files were combined together. The glytoucan_ac was mapped to chebi_id using another input file. Additionally, two new columns uniprot_ac and tax_id were added in the output file. The following filtering rules wer applied: 1) Only those protein + site were inlcuded which are present in UniProtKB database 2) Only those rows were included where a valid ChEBI ID was present. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The file includes glycan annotation (GlyTouCan ac and ChEBI Id) for the protein + site included in UniProtKB(https://uniprot.org/) database. "],"etag":"b2071c8ec1dccdc98d52cf870084be57","io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_chebi.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv","filename":"protein_glygen_uniprotkb_protvista_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_uniprotkb_protvista_mapping.stat.csv","filename":"protein_glygen_uniprotkb_protvista_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:01.020000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000556/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000556/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bba19cafab0899b87234f2d66add03b5bd3aae560aea4223923d2b851584e106","provenance_domain":{"name":"Glycan Citations (GlycoMotif)","version":"v-0.0.0","created":"2021-03-16T15:44:18.145789","modified":"2024-05-17T11:24:04.539Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlycoMotif (https://glycomotif.glyomics.org/). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281) and the associated PMIDs are derived from the Glycan Motif dataset (https://data.glygen.org/GLY_000283)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations","Motif"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the associated PMIDs for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list. The MEDLINE format is used to add Journal, Author, Title detail associated with the publications. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_motif.csv","filename":"glycan_citations_motif.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_motif.stat.csv","filename":"glycan_citations_motif.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations(GlycoMotif)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-17T11:24:04.539882Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000556/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000556/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations(GlycoMotif)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Citations (GlycoMotif)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-03-16T15:44:18.145789","modified":"2022-09-26T09:08:12.629423","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_motif.csv","filename":"glycan_motif.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_citations_glycomotif.csv","filename":"glycan_citations_glycomotif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the associated PMIDs for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list. The MEDLINE format is used to add Journal, Author, Title detail associated with the publications. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlycoMotif (https://glycomotif.glyomics.org/glycomotif/GlycoMotif). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281) and the associated PMIDs is derived from file Glycan Motif(https://data.glygen.org/GLY_000283)."],"etag":"6b3c316dc884c5bb2f67c60dda01509c316e012eee464cc97ed243c18532fff2","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_motif.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_motif.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_glycomotif.csv","filename":"glycan_citations_glycomotif.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_glycomotif.stat.csv","filename":"glycan_citations_glycomotif.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.734000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000556/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000556/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"15130e06ddc8d41ee031e7ccf1cbaca5","provenance_domain":{"name":"Glycan Citations (GlycoMotif)","version":"v-2.1.1","created":"2021-03-16T15:44:18.145789","modified":"2023-03-14T16:51:16.564Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlycoMotif (https://glycomotif.glyomics.org/). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281) and the associated PMIDs are derived from the Glycan Motif dataset (https://data.glygen.org/GLY_000283)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations","Motif"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_motif.csv","filename":"glycan_motif.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_citations_motif.csv","filename":"glycan_citations_motif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the associated PMIDs for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list. The MEDLINE format is used to add Journal, Author, Title detail associated with the publications. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_motif.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_motif.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_motif.csv","filename":"glycan_citations_motif.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_motif.stat.csv","filename":"glycan_citations_motif.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations(GlycoMotif)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:33:53.253000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000557/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000557/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"glycan dictionary","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan structure dictionary","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-03-31T13:03:41.839695","modified":"2024-06-03T22:00:07.194Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan dictionary","structure","glycan"],"pipeline_steps":[{"input_list":[],"description":"The glycan dictionary was manually generated using multiple resources. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"usability_domain":["Glycan dictionary is a list of terms which describe some structural aspect of the glycan composition or structure. The terms are extracted with a combination of manual and automatic literature mining tools from various sources. It is an on-going process and the current list includes 180 terms..The terms can also be viewed on the GlyGen wikipedia:https://wiki.glygen.org/index.php/Glycan_structure_dictionary. To submit more terms please follow instructions provided on the GlyGen wikipedia page. "],"etag":"3eb104a1d2f8afbfef2d642f11e98f84c4d1d7bfe1b7744cce83acab52a15db0","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_dictionary.stat.csv","filename":"glycan_dictionary.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":498,"last_update":"2024-06-03T22:00:07.194034Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000557/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000557/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"glycan","category_name":"molecule"},{"category_value":"glycan dictionary","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan structure dictionary","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":[],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":[],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"created":"2021-03-31T13:03:41.839695","modified":"2022-09-26T09:08:12.550174","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan dictionary","structure","glycan"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2wwwdownloads/v-2.0.2/12_08_2021/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}],"prerequisite":[],"description":"The glycan dictionary was manually generated using multiple resources. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Glycan dictionary is a list of terms which describe some structural aspect of the glycan composition or structure. The terms are extracted with a combination of manual and automatic literature mining tools from various sources. It is an on-going process and the current list includes 180 terms..The terms can also be viewed on the GlyGen wikipedia:https://wiki.glygen.org/index.php/Glycan_structure_dictionary. To submit more terms please follow instructions provided on the GlyGen wikipedia page. "],"etag":"d162acdeb777197b69ff65058c130644ab4d9abd7f4a26a518e88550f4e6c2e4","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_dictionary.csv","uri":"https:/data.glygen.org/ln2downloads/glycan_dictionary/12_08_2021/glycan_dictionary.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_dictionary.stat.csv","filename":"glycan_dictionary.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.428000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000557/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000557/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"glycan","category_name":"molecule"},{"category_value":"glycan dictionary","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan structure dictionary","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":[],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":[],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-03-31T13:03:41.839695","modified":"2022-09-26T09:08:12.550174","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan dictionary","structure","glycan"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2wwwdownloads/v-2.1.1/12_08_2021/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}],"prerequisite":[],"description":"The glycan dictionary was manually generated using multiple resources. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["Glycan dictionary is a list of terms which describe some structural aspect of the glycan composition or structure. The terms are extracted with a combination of manual and automatic literature mining tools from various sources. It is an on-going process and the current list includes 180 terms..The terms can also be viewed on the GlyGen wikipedia:https://wiki.glygen.org/index.php/Glycan_structure_dictionary. To submit more terms please follow instructions provided on the GlyGen wikipedia page. "],"etag":"724ace7dbe04bb3de109b30dbc7e5cae","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_dictionary.csv","uri":"/data/shared/glyds/downloads/glycan_dictionary/03_03_2023/glycan_dictionary.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_dictionary.stat.csv","filename":"glycan_dictionary.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:01.344000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000559/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000559/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"byonic sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan sequences Byonic","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-06-02T12:48:41.483014","modified":"2024-05-17T11:24:04.621Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Byonic"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"A python script is used to generate the byonic format based on the compositioon for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in Byonic format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://dev.glycam.org/"],"etag":"706bb51a1a6a8a3c0430703693a3c4cb2ab93961efe0c2f6b64e371091601896","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_byonic.csv","filename":"glycan_sequences_byonic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_byonic.stat.csv","filename":"glycan_sequences_byonic.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":273,"last_update":"2024-05-17T11:24:04.621122Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000559/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000559/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"byonic sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan sequences Byonic","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-02T12:48:41.483014","modified":"2022-09-26T09:08:12.680882","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Byonic"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_sequences_byonic.csv","filename":"glycan_sequences_byonic.csv"}],"prerequisite":[],"description":"A python script is used to generate the byonic format based on the compositioon for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in Byonic format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://dev.glycam.org/"],"etag":"e7a9c8fc7a3766cc7e984e2fd56a42dcaf4ebd3c0c0b0105b9e7945e25f1077d","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_byonic.csv","filename":"glycan_sequences_byonic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_byonic.stat.csv","filename":"glycan_sequences_byonic.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.739000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000559/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000559/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"byonic sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan sequences Byonic","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-06-02T12:48:41.483014","modified":"2022-09-26T09:08:12.680882","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Byonic"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_sequences_byonic.csv","filename":"glycan_sequences_byonic.csv"}],"prerequisite":[],"description":"A python script is used to generate the byonic format based on the compositioon for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides the glycan sequences in Byonic format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://dev.glycam.org/"],"etag":"61542785a0789a05acd3494d7a403449","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"names.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/names.tsv"}},{"uri":{"filename":"subsumption.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_byonic.csv","filename":"glycan_sequences_byonic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_byonic.stat.csv","filename":"glycan_sequences_byonic.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:01.549000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000560/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000560/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cbfc94e83be455e98ade03ef84134e644438546addbaf7d14d5538478009dceb","provenance_domain":{"name":"Human Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-03T16:32:02.053252","modified":"2024-05-17T11:24:04.661Z","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Proteoform Glycosylation Citations (UniProtKB) dataset contains Homo sapiens [taxid:9606] citation details of the publications present in the dataset Human Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000038)."],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":235,"last_update":"2024-05-17T11:24:04.661776Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000560/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000560/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Proteoform Glycosylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T16:32:02.053252","modified":"2022-09-26T09:08:12.586861","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"dafdb93217aa8a8c0e8d5de8ba99a9e2a37fb946813e17f28b1d45e3b83b832c","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_uniprotkb.csv","filename":"human_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"human_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.708000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000560/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000560/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fd84278012893bf05ddf848a3af14075","provenance_domain":{"name":"Human Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-03T16:32:02.053252","modified":"2023-03-14T16:52:07.896Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:01.737000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000561/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000561/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4133dfe7ba91e1da57824254efb01a257ab41bcba5dcefbc840a29e371c65f8b","provenance_domain":{"name":"Mouse Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-03T16:33:45.288361","modified":"2024-06-03T22:32:02.142Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse Proteoform Glycosylation Citations (UniProtKB) dataset contains Mus musculus [taxid:10090] citation details of the publications present in the dataset Mouse Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000039)."],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":236,"last_update":"2024-06-03T22:32:02.142257Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000561/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000561/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteoform Glycosylation Citations (UniProtKB)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-06-03T16:33:45.288361","modified":"2022-01-20T16:08:16.713145","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"3e9b6ebe91930bf430ab6e62f3992f78","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_uniprotkb.csv","filename":"mouse_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"mouse_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.414000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000561/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000561/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6b3ae04e693a4de29ba1cdc658701a0e","provenance_domain":{"name":"Mouse Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-03T16:33:45.288361","modified":"2023-03-14T16:53:05.178Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:01.923000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000562/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000562/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"721104b2022a9f001bf0bad61c891d84e0e3cfdab5373eb9566c6d7204bc0cba","provenance_domain":{"name":"Rat Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-03T16:35:03.994318","modified":"2024-05-17T11:24:04.739Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Proteoform Glycosylation Citations (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] citation details of the publications present in the dataset Rat Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000224)."],"description_domain":{"keywords":["citations","glycosylation","UniProtKB"]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Citation Glycosylation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":237,"last_update":"2024-05-17T11:24:04.739010Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000562/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000562/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Citation Glycosylation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Proteoform Glycosylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T16:35:03.994318","modified":"2022-09-26T09:08:12.695132","version":"v-2.0.2"},"description_domain":{"keywords":["citations","glycosylation","UniProtKB"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"11d3d46fa9b901cfba01e0b0fb68fb18b141f52c4147f68b0f1f0fc3527d406d","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_uniprotkb.csv","filename":"rat_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"rat_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.620000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000562/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000562/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b8c8e225a9595fca6f6c49ae4c5016e2","provenance_domain":{"name":"Rat Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-03T16:35:03.994318","modified":"2023-03-14T16:54:07.445Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":["citations","glycosylation","UniProtKB"],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Citation Glycosylation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:02.116000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000563/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000563/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b2baddc3e48a52f0d0c6139ae1bc1a546169d5b6d254f7fa3f68d27956307852","provenance_domain":{"name":"HCV1a Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-03T16:45:27.957904","modified":"2024-05-17T11:24:04.779Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1a Proteoform Glycosylation Citations (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] citation details of the publications present in the dataset HCV1a Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000382)."],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":255,"last_update":"2024-05-17T11:24:04.779939Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000563/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000563/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1a Proteoform Glycosylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T16:45:27.957904","modified":"2022-09-26T09:08:12.675490","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"f11cb2bde058589ac6e45c118d9ec39c9d6ec3747c0064afa0aafb1d0df9b5c8","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_citations_glycosylation_uniprotkb.csv","filename":"hcv1a_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"hcv1a_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.639000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000563/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000563/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1997aeefa9392b1f1a987ae0fc1c5e36","provenance_domain":{"name":"HCV1a Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-03T16:45:27.957904","modified":"2023-03-14T16:54:52.361Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:02.304000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000564/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000564/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"617df639247337dc08b5cc41425269e79fc00754a486c8391ccfde000bcd941e","provenance_domain":{"name":"HCV1b Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-03T16:48:21.811587","modified":"2024-05-17T11:24:04.819Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1b Proteoform Glycosylation Citations (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] citation details of the publications present in the dataset HCV1b Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000383)."],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Citations Glycosylation Sites UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":260,"last_update":"2024-05-17T11:24:04.819877Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000564/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000564/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Citations Glycosylation Sites UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"HCV1b Proteoform Glycosylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T16:48:21.811587","modified":"2022-09-26T09:08:12.767605","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"4757c5f2ee05629a5af3da6100bc782ba19677a6f69ecd71ec0b115536e74644","io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_citations_glycosylation_uniprotkb.csv","filename":"hcv1b_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"hcv1b_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.643000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000564/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000564/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"32564000faf6f9621c6518e63b8642a5","provenance_domain":{"name":"HCV1b Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-03T16:48:21.811587","modified":"2023-03-14T16:55:29.098Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Citations Glycosylation Sites UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:02.499000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000565/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000565/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fa52c9de7e46a4b4a84b0f36829ca6dc4773fc4fcabcfea033325577b1e061db","provenance_domain":{"name":"SARS-CoV2 Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-03T16:50:40.376491","modified":"2024-05-17T11:24:04.863Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV2 Proteoform Glycosylation Citations (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] citation details of the publications present in the dataset SARS-CoV2 Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000473)."],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Citation Glycosylation sites UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":281,"last_update":"2024-05-17T11:24:04.863792Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000565/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000565/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Citation Glycosylation sites UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV2 Proteoform Glycosylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T16:50:40.376491","modified":"2022-09-26T09:08:12.714891","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"55c0c83b864d58c98c04b310cfcfc1dfa29423799a3a4098036f9ae220d75e42","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_proteoform_citations_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov2_proteoform_citations_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_uniprotkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.464000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000565/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000565/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b35e19b40671a41d7375bc7662df085d","provenance_domain":{"name":"SARS-CoV2 Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-03T16:50:40.376491","modified":"2023-03-14T16:56:09.877Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_proteoform_citations_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov2_proteoform_citations_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Citation Glycosylation sites UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:02.700000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000566/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000566/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8fdd50b04e328498960db8eef0463f0b4e1f545fa20d5ff3e53b9fed6a21dc16","provenance_domain":{"name":"SARS-CoV1 Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-03T16:51:57.418753","modified":"2025-10-09T14:19:10.330Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV1 Proteoform Glycosylation Citations (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] citation details of the publications present in the dataset SARS-CoV1 Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000495)."],"description_domain":{"keywords":["Citation","PubMed","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"glycosylation citation UniProtKB","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2025-10-09T14:19:10.330874Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000566/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000566/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"glycosylation citation UniProtKB","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"SARS-CoV1 Proteoform Glycosylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T16:51:57.418753","modified":"2022-09-26T09:08:12.532147","version":"v-2.0.2"},"description_domain":{"keywords":["Citation","PubMed","UniProtKB"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"7c3b07fff5f6935e455f857435ffce184c062f5e6a94836524958b5c5e7e6705","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_uniprotkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.521000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000566/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000566/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3b8273aeb996449077d376beb67e8dab","provenance_domain":{"name":"SARS-CoV1 Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-03T16:51:57.418753","modified":"2023-03-14T16:57:02.366Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":["Citation","PubMed","UniProtKB"],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"glycosylation citation UniProtKB","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:02.905000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000567/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000567/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d3bab9935452d0c3c91767af01d06c25400d124b297650b536d6ca9726dc7664","provenance_domain":{"name":"Human Proteoform Phosphorylation Citations (iPTMnet)","version":"v-0.0.0","created":"2021-06-03T17:29:17.656153","modified":"2024-12-05T19:29:39.732Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Proteoform Citations (iPTMNet) contains Homo sapiens [taxid:9606] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"human_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"human_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":417,"last_update":"2024-12-05T19:29:39.732453Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000567/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000567/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Proteoform Phosphorylation Citations (iPTMnet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T17:29:17.656153","modified":"2022-09-26T09:08:12.453738","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"6a18fec0f70c6f3859fd56bfb7dc997b715851f5778ddea8c08ffe88c16f2cd9","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_phosphorylation_iptmnet.csv","filename":"human_proteoform_citations_phosphorylation_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_phosphorylation_iptmnet.stat.csv","filename":"human_proteoform_citations_phosphorylation_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.687000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000567/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000567/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dd9abe4e4437ff01da2209190b3cfffe","provenance_domain":{"name":"Human Proteoform Phosphorylation Citations (iPTMnet)","version":"v-2.1.1","created":"2021-06-03T17:29:17.656153","modified":"2023-03-14T16:58:11.505Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"human_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"human_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:03.104000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000568/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000568/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ef5d28d1e6f13e0c6cc3d55a956ad3c3323d18b82722d783e49bfe786ce14951","provenance_domain":{"name":"Mouse Proteoform Phosphorylation Citations (iPTMnet)","version":"v-x.x.x","created":"2021-06-03T17:31:30.200524","modified":"2024-12-05T19:36:18.634Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Proteoform Citations (iPTMNet) contains Mus musculus [taxid:10090] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":419,"last_update":"2024-12-05T19:36:18.634703Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000568/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000568/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Proteoform Phosphorylation Citations (iPTMnet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T17:31:30.200524","modified":"2022-09-26T09:08:12.752793","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"5081391a5d815a8ff1fdd241ca0922a5e3fa3c90f282331fe61243a75351bbb7","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_phosphorylation_iptmnet.csv","filename":"mouse_proteoform_citations_phosphorylation_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_phosphorylation_iptmnet.stat.csv","filename":"mouse_proteoform_citations_phosphorylation_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.721000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000568/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000568/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2f413778fd105ea49ec466a5c36df089","provenance_domain":{"name":"Mouse Proteoform Phosphorylation Citations (iPTMnet)","version":"v-2.1.1","created":"2021-06-03T17:31:30.200524","modified":"2023-03-14T16:58:53.981Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:03.303000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000569/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000569/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"012e283834e1d04fc454ad86ff4864f35b2c93b23d3c7180688d4e8609d5b093","provenance_domain":{"name":"Rat Proteoform Phosphorylation Citations (iPTMnet)","version":"v-0.0.0","created":"2021-06-03T17:35:01.843447","modified":"2024-12-05T19:37:20.742Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Proteoform Citations (iPTMNet) contains Rattus norvegicus [taxid:10116] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"rat_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"rat_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":422,"last_update":"2024-12-05T19:37:20.742403Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000569/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000569/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Proteoform Phosphorylation Citations (iPTMnet)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T17:35:01.843447","modified":"2022-09-26T09:08:12.731602","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"e890ec431021942372d2f8ac52e2eff311c85c12d1e2fce13bc240bca4da7f0f","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_phosphorylation_iptmnet.csv","filename":"rat_proteoform_citations_phosphorylation_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_phosphorylation_iptmnet.stat.csv","filename":"rat_proteoform_citations_phosphorylation_iptmnet.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.506000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000569/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000569/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9a693abb9faaea39fa9f2c3d39921454","provenance_domain":{"name":"Rat Proteoform Phosphorylation Citations (iPTMnet)","version":"v-2.1.1","created":"2021-06-03T17:35:01.843447","modified":"2023-03-14T16:59:29.612Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"rat_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"rat_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:03.505000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000570/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000570/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Reactions (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-06-03T17:38:21.320871","modified":"2024-05-17T11:24:05.062Z","version":"v-0.0.0"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"e4801832fa58a2bc31b741e082d6b9eb709b301ab6a9c1d0ba0b3a26376d8e45","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_reactions_rhea.csv","filename":"human_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_reactions_rhea.stat.csv","filename":"human_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:05.062874Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000570/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000570/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Reactions (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T17:38:21.320871","modified":"2022-09-26T09:08:12.535086","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"8e66ebad5c7e4c10b5dbfeedf5258d0f4e7fae57b5b17816081ab8db01884d37","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_reactions_rhea.csv","filename":"human_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_reactions_rhea.stat.csv","filename":"human_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.005000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000570/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000570/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Reactions (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-06-03T17:38:21.320871","modified":"2022-09-26T09:08:12.535086","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"afd775e6101db00ef1b66faa3a6401c6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_reactions_rhea.csv","filename":"human_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_reactions_rhea.stat.csv","filename":"human_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:03.697000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000571/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000571/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"df632172578b829bd60728a2471e64cd8dfc0275a0299152abea04c8be4ebbf7","provenance_domain":{"name":"Mouse Reactions Rhea","version":"v-0.0.0","created":"2021-06-03T17:42:22.390280","modified":"2025-03-06T15:35:31.306Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Reactions (Rhea) dataset offers detailed information on enzymatic pathways and equations involved in chemical and transport reactions specific to Mus musculus [TaxID: 10090]. Rhea is a rigorously curated knowledgebase that catalogs biologically significant reactions and serves as the authoritative standard for enzyme and transporter annotation in UniProtKB. To characterize reaction participants, Rhea leverages the Chemical Entities of Biological Interest (ChEBI) dictionary. "],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_reactions_rhea.csv","filename":"mouse_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_reactions_rhea.stat.csv","filename":"mouse_protein_reactions_rhea.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":591,"last_update":"2025-03-06T15:35:31.306846Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000571/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000571/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Reactions Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T17:42:22.390280","modified":"2022-09-26T09:08:12.450397","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"90d5edf87dbd1661d4a8a8df430343bf378f65b02f8b75037f745312668aa165","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_reactions_rhea.csv","filename":"mouse_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_reactions_rhea.stat.csv","filename":"mouse_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.961000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000571/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000571/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Reactions Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-06-03T17:42:22.390280","modified":"2022-09-26T09:08:12.450397","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"fb2464e6fddc2fbcb89c2f042a2648b6","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_reactions_rhea.csv","filename":"mouse_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_reactions_rhea.stat.csv","filename":"mouse_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:03.906000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000572/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000572/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0ee42b73ce790011ec679e222522670ad091fbd7024a960c9f4e75a0e59db89a","provenance_domain":{"name":"Rat Reactions (Rhea)","version":"v-0.0.0","created":"2021-06-03T17:43:30.579234","modified":"2025-03-06T15:35:00.039Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Recactions (Rhea) dataset offers detailed information on enzymatic pathways and equations involved in chemical and transport reactions specific to Rattus norvegicus [TaxID: 10116]. Rhea is a rigorously curated knowledgebase that catalogs biologically significant reactions and serves as the authoritative standard for enzyme and transporter annotation in UniProtKB. To characterize reaction participants, Rhea leverages the Chemical Entities of Biological Interest (ChEBI) dictionary."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_reactions_rhea.csv","filename":"rat_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_reactions_rhea.stat.csv","filename":"rat_protein_reactions_rhea.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":595,"last_update":"2025-03-06T15:35:00.039225Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000572/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000572/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Reactions (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-03T17:43:30.579234","modified":"2022-09-26T09:08:12.766326","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"d89e4ec2b28f8fd5b5c03112a61660d43ac0d958d9eb9a6682bced9914a85b6b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_reactions_rhea.csv","filename":"rat_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_reactions_rhea.stat.csv","filename":"rat_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.020000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000572/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000572/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Reactions (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-06-03T17:43:30.579234","modified":"2022-09-26T09:08:12.766326","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"7906164d5ecdcc2f3935bb4b92f39fd8","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_reactions_rhea.csv","filename":"rat_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_reactions_rhea.stat.csv","filename":"rat_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:04.106000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000573/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000573/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e3a4d008c9473ea0a223e1810b9ec8cf865e43e145fa65e3b8d7e147b2919a95","provenance_domain":{"name":"Mouse Proteoform Citations (Literature Mining)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-06-04T10:20:39.827303","modified":"2025-04-15T14:29:15.805Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Proteoform Citations [Automatic Literature Mining] dataset contains Mus musculus [taxid:10090] citation details of the publications present in the Mouse Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_000492)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":344,"last_update":"2025-04-15T14:29:15.805753Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000573/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000573/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteoform Citations (Literature Mining)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-04T10:20:39.827303","modified":"2022-09-26T09:08:12.716479","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_citations_literature_mining.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_literature_mining.csv","filename":"mouse_proteoform_citations_glycosylation_literature_mining.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000481. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"7f1a49ca7af29a145bdf3d74e86a0a82e60cb256bb5d276441752f85b394018d","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_literature_mining.csv","filename":"mouse_proteoform_citations_glycosylation_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_literature_mining.stat.csv","filename":"mouse_proteoform_citations_glycosylation_literature_mining.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.593000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000573/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000573/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5eabe97f8d8548c06afd19d76c5ae067","provenance_domain":{"name":"Mouse Proteoform Citations (Literature Mining)","version":"v-2.1.1","created":"2021-06-04T10:20:39.827303","modified":"2023-03-14T17:00:09.743Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000481. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_citations_literature_mining.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:04.308000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000574/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000574/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"888f20fb8bf1999bc4e7b0843aa2e0ad9f239cf92af6ad845b4931c3caebac0d","provenance_domain":{"name":"Rat Proteoform Citations (Literature Mining)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-06-04T10:25:25.298469","modified":"2025-04-15T14:32:08.225Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Proteoform Citations [Automatic Literature Mining] dataset contains Rattus norvegicus [taxid:10116] citation details of the publications present in the Rat [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_000493)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":321,"last_update":"2025-04-15T14:32:08.225279Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000574/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000574/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteoform Citations (Literature Mining)","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-04T10:25:25.298469","modified":"2022-09-26T09:08:12.694060","version":"v-2.0.2"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_citations_literature_mining.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_literature_mining.csv","filename":"rat_proteoform_citations_glycosylation_literature_mining.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000481. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"etag":"8dd2c20c02ef8348f7f3ab614cbc4a564052827c9e5f0575ad6c11158f8bff26","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_literature_mining.csv","filename":"rat_proteoform_citations_glycosylation_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_literature_mining.stat.csv","filename":"rat_proteoform_citations_glycosylation_literature_mining.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.551000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000574/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000574/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7eac94d53ea0067e1d9e607eae380f86","provenance_domain":{"name":"Rat Proteoform Citations (Literature Mining)","version":"v-2.1.1","created":"2021-06-04T10:25:25.298469","modified":"2023-03-14T17:00:46.458Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000481. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_literature_mining.csv","filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:04.514000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000575/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000575/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"526d1116219b0211b82d6f02f086125061ef0cc41c3c4feec246e60258f439bd","provenance_domain":{"name":"Human Proteoform Glycation Citations (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-06-04T12:34:52.072705","modified":"2024-05-17T11:24:05.260Z","derived_from":[],"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Human Proteoform Glycation Citations (UniProtKB) dataset contains human [taxid:9606] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.csv","filename":"human_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.stat.csv","filename":"human_proteoform_citations_glycation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":270,"last_update":"2024-05-17T11:24:05.260806Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000575/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000575/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Proteoform Glycation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-04T12:34:52.072705","modified":"2022-09-26T09:08:12.677186","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"3562607638c39a0e500983ef11782acd18e3755fadc37d7fc609a7975a0ea2c3","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycation_uniprotkb.csv","filename":"human_proteoform_citations_glycation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_glycation_uniprotkb.stat.csv","filename":"human_proteoform_citations_glycation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.762000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000575/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000575/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"96868dc97e34176eeb426084fe0ac53f","provenance_domain":{"name":"Human Proteoform Glycation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-04T12:34:52.072705","modified":"2023-03-14T17:01:29.034Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[{"step_number":-1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","prerequisite":[{"name":"","uri":{"uri":""}}],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycation_sites_uniprotkb.csv","filename":"human_proteoform_glycation_sites_uniprotkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.csv","filename":"human_proteoform_citations_glycation_sites_uniprotkb.csv"}]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.csv","filename":"human_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.stat.csv","filename":"human_proteoform_citations_glycation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:04.704000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000577/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000577/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2ed65821e2a51107980c05528dbc7f4ba7f68d43b6445a623eb39738032e8ee5","provenance_domain":{"name":"Rat Proteoform Glycation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-06-04T12:39:47.848113","modified":"2024-05-17T11:24:05.298Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_citations_glycation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:05.298092Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000577/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000577/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Rat Proteoform Glycation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-06-04T12:39:47.848113","modified":"2022-09-26T09:08:12.580817","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"3eda18966b83d858c867a39fba6918d65438b86a095f6c65bf9e639e8b7f4a48","io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycation_uniprotkb.csv","filename":"rat_proteoform_citations_glycation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycation_uniprotkb.stat.csv","filename":"rat_proteoform_citations_glycation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.097000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000577/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000577/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e44c1cd6e18d2abc9dab69970f8fbad3","provenance_domain":{"name":"Rat Proteoform Glycation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-06-04T12:39:47.848113","modified":"2023-03-14T17:02:09.831Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":[],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_citations_glycation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:04.905000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000578/DRAFT","contents":{"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_gptwiki.csv","filename":"glycan_xref_gptwiki.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_gptwiki.stat.csv","filename":"glycan_xref_gptwiki.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GPTWiki cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T12:30:31.036377","modified":"2024-05-17T11:24:05.335Z","version":"v-0.0.0","name":"Glycan xref GPTwiki"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GPTWiki","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GPTWiki ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database:https://gptwiki.glyomics.org/"],"object_id":"https://biocomputeobject.org/GLY_000578/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"13c4f576262036edbab97f8ac21f193bbf96d000e7fa5f50e2c8b6d0ebb50fa1","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":273,"last_update":"2024-05-17T11:24:05.335758Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000578/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycosites.csv","uri":"https:/data.glygen.org/ln2downloads/gptwiki/gpt_2021_06_23_14_51_10/glycosites.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_gptwiki.csv","filename":"glycan_xref_gptwiki.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_gptwiki.stat.csv","filename":"glycan_xref_gptwiki.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GPTWiki cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T12:30:31.036377","modified":"2022-09-26T09:08:12.705345","version":"v-2.0.2","name":"Glycan xref GPTwiki"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GPTWiki","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_gptwiki.csv","filename":"glycan_xref_gptwiki.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GPTWiki ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database:https://gptwiki.glyomics.org/"],"object_id":"https://biocomputeobject.org/GLY_000578/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0ac25279d03c5e353a9783ec1f75baafa3ad4d05cb23d58f4dd476981381acb2","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:51.044000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000578/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycosites.csv","uri":"/data/shared/glyds/downloads/gptwiki/gpt_2021_06_23_14_51_10/glycosites.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_gptwiki.csv","filename":"glycan_xref_gptwiki.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_gptwiki.stat.csv","filename":"glycan_xref_gptwiki.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GPTWiki cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T12:30:31.036377","modified":"2022-09-26T09:08:12.705345","version":"v-2.1.1","name":"Glycan xref GPTwiki"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GPTWiki","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_gptwiki.csv","filename":"glycan_xref_gptwiki.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GPTWiki ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database:https://gptwiki.glyomics.org/"],"object_id":"https://biocomputeobject.org/GLY_000578/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"252cd7353ae1d2e8e31293e64575493f","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:05.098000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000579/DRAFT","contents":{"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glycosmos.csv","filename":"glycan_xref_glycosmos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_glycosmos.stat.csv","filename":"glycan_xref_glycosmos.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosmos cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T12:41:06.708128","modified":"2024-05-17T11:24:05.372Z","version":"v-0.0.0","name":"Glycan Xref Glycosmos"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosmos","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to Glycosmos ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glycosmos.org/"],"object_id":"https://biocomputeobject.org/GLY_000579/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e8e2000c7d9c54f7fd68f19cda8c21fe419ff8c3059dcd5f8867acb9d0af9f7e","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":269,"last_update":"2024-05-17T11:24:05.372839Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000579/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycosmos.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/glycosmos.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glycosmos.csv","filename":"glycan_xref_glycosmos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_glycosmos.stat.csv","filename":"glycan_xref_glycosmos.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosmos cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T12:41:06.708128","modified":"2022-09-26T09:08:12.658977","version":"v-2.0.2","name":"Glycan Xref Glycosmos"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosmos","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycosmos.tsv","filename":"glycosmos.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_glycosmos.csv","filename":"glycan_xref_glycosmos.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to Glycosmos ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glycosmos.org/"],"object_id":"https://biocomputeobject.org/GLY_000579/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bf0abf598f6795f7a218fde32dfb9c1eab893bef1755d35085fe0232649d2679","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.390000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000579/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycosmos.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/glycosmos.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glycosmos.csv","filename":"glycan_xref_glycosmos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_glycosmos.stat.csv","filename":"glycan_xref_glycosmos.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosmos cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T12:41:06.708128","modified":"2022-09-26T09:08:12.658977","version":"v-2.1.1","name":"Glycan Xref Glycosmos"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosmos","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycosmos.tsv","filename":"glycosmos.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_glycosmos.csv","filename":"glycan_xref_glycosmos.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to Glycosmos ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glycosmos.org/"],"object_id":"https://biocomputeobject.org/GLY_000579/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7c415557c3cbb9f778ccbf94147e81ae","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:05.288000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000580/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000580/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"077efbb60b591be53d20e166f85b0e9b13f8f26787b7ba70510d96db08128734","provenance_domain":{"name":"Glycan sequence GWB","version":"v-0.0.0","created":"2021-08-02T12:45:09.980974","modified":"2024-05-17T11:24:05.411Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in GlycoWorkBench format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GWB"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"A python script is used to generate the GlycoWorkBench format based on the compositioon for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_gwb.csv","filename":"glycan_sequences_gwb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_gwb.stat.csv","filename":"glycan_sequences_gwb.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GWB sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":239,"last_update":"2024-05-17T11:24:05.411441Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000580/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_gwb.csv","filename":"glycan_sequences_gwb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_gwb.stat.csv","filename":"glycan_sequences_gwb.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GWB sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","providedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T12:45:09.980974","modified":"2022-09-26T09:08:12.655194","version":"v-2.0.2","name":"Glycan sequence GWB"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GWB"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_sequences_gwb.csv","filename":"glycan_sequences_gwb.csv"}],"prerequisite":[],"description":"A python script is used to generate the GlycoWorkBench format based on the compositioon for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the glycan sequences in GlycoWorkBench format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). "],"object_id":"https://biocomputeobject.org/GLY_000580/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"db26ec130e943a1ef65edfd4066703b870ab433f6f56bc3f10e90f630af2be11","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.537000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000580/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000580/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b2f00b537b088e9fd6c930e120f5a98f","provenance_domain":{"name":"Glycan sequence GWB","version":"v-2.1.1","created":"2021-08-02T12:45:09.980974","modified":"2023-02-15T19:17:04.834Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides the glycan sequences in GlycoWorkBench format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GWB"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/monocomp.tsv","filename":"monocomp.tsv"},{"uri":"https:/data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/gwb.zip","filename":"gwb.zip"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_sequences_gwb.csv","filename":"glycan_sequences_gwb.csv"}],"prerequisite":[],"description":"A python script is used to generate the GlycoWorkBench format based on the compositioon for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocomp.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_gwb.csv","filename":"glycan_sequences_gwb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_gwb.stat.csv","filename":"glycan_sequences_gwb.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GWB sequence format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:08:18.922000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000582/DRAFT","contents":{"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:33:34.395747","modified":"2024-05-21T15:34:36.222Z","version":"v-0.0.0","name":"Human glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human glycosylation sites [Automatic literature Mining] [Manually verified] dataset contains a list of Homo sapiens [taxid:9606] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000001)."],"object_id":"https://biocomputeobject.org/GLY_000582/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"97c1a530f52de4fc84f573a84eb2e1944955857cbebf031d5ee7af08978eef34"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":670,"last_update":"2024-05-21T15:34:36.222805Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000582/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:33:34.395747","modified":"2022-09-26T09:08:12.559953","version":"v-2.0.2","name":"Human glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000582/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e37cc785d7949d8b0c62f6b4e13b94008e5608f9e382f65748fa797156db2570"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.658000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000582/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:33:34.395747","modified":"2022-09-26T09:08:12.559953","version":"v-2.1.1","name":"Human glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000582/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dd11c18333cf2ed5c5d42f8abe03ac35"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:05.611000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000583/DRAFT","contents":{"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:48:30.176124","modified":"2024-05-21T15:35:20.961Z","version":"v-0.0.0","name":"Mouse glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse glycosylation sites [Automatic literature Mining] [Manually verified] dataset contains a list of Mus musculus [taxid:10090] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000007)."],"object_id":"https://biocomputeobject.org/GLY_000583/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b176a850dba4b5bc759efc8c0fb126973ac53fd39af3934df44caa35495d8947"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":671,"last_update":"2024-05-21T15:35:20.961678Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000583/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:48:30.176124","modified":"2022-09-26T09:08:12.600491","version":"v-2.0.2","name":"Mouse glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000583/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1519db0940013a2fcfc1a4bc268395826cf8f06dff2521b1975a8e9bfd204dec"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.513000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000583/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:48:30.176124","modified":"2022-09-26T09:08:12.600491","version":"v-2.1.1","name":"Mouse glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000583/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e857a514529bf89c3b89a00d30a7a9f0"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:05.819000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000584/DRAFT","contents":{"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:52:48.556455","modified":"2024-05-21T15:36:02.950Z","version":"v-0.0.0","name":"Rat glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Rat glycosylation sites [Automatic literature Mining] [Manually verified] dataset contains a list of Rattus norvegicus [taxid:10116] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000244)."],"object_id":"https://biocomputeobject.org/GLY_000584/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4b120be9cb369308023f2d4bddfb07fbb18afad2f9468da23f6408124d80143c"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":674,"last_update":"2024-05-21T15:36:02.950752Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000584/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:52:48.556455","modified":"2022-09-26T09:08:12.479391","version":"v-2.0.2","name":"Rat glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000584/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1957edc1e0f054cfa0a1eaf13628b5b63dd20e6eea088379dd12a35738b85f70"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.794000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000584/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"affiliation":"GlyConnect","contribution":["curatedBy"],"name":"Catherine Hayes","email":"hayescat@gmail.com"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-08-02T15:52:48.556455","modified":"2022-09-26T09:08:12.479391","version":"v-2.1.1","name":"Rat glycosylation sites [Automatic literature Mining] [Manually verified]"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"object_id":"https://biocomputeobject.org/GLY_000584/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a649a7162bf887be5d727b63ef263ad9"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:06.018000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000587/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000587/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"GlyTouCan masterlist","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-08-18T13:48:00.328077","modified":"2024-05-17T11:24:05.557Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to process the dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides all glycans (identified by GlyTouCan accession) from GlyTouCan. Source database: https://glytoucan.org/. "],"etag":"596cb87a9c20db2d076a66a18fe16b0f213dd98584b9bba78422403a244db54c","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_glytoucanidlist.csv","filename":"glycan_glytoucanidlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_glytoucanidlist.stat.csv","filename":"glycan_glytoucanidlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":126,"last_update":"2024-05-17T11:24:05.557042Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000587/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000587/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"GlyTouCan masterlist","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-08-18T13:48:00.328077","modified":"2022-09-26T09:08:12.754125","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glytoucan_allacc.txt","filename":"glytoucan_allacc.txt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_glytoucanidlist.csv","filename":"glycan_glytoucanidlist.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to process the dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides all glycans (identified by GlyTouCan accession) from GlyTouCan. Source database: https://glytoucan.org/. "],"etag":"9a6a5e75b7ab8b2cdd8d6b67bddbb81274a22efaa36acacac7d9eeb1167f2367","io_domain":{"input_subdomain":[{"uri":{"filename":"glytoucan_allacc.txt","uri":"https:/data.glygen.org/ln2downloads/glycan_list/05_17_2021/glytoucan_allacc.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_glytoucanidlist.csv","filename":"glycan_glytoucanidlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_glytoucanidlist.stat.csv","filename":"glycan_glytoucanidlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.499000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000587/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000587/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"GlyTouCan masterlist","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-08-18T13:48:00.328077","modified":"2022-09-26T09:08:12.754125","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glytoucan_allacc.txt","filename":"glytoucan_allacc.txt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_glytoucanidlist.csv","filename":"glycan_glytoucanidlist.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to process the dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides all glycans (identified by GlyTouCan accession) from GlyTouCan. Source database: https://glytoucan.org/. "],"etag":"35578d31d637fc8a099533e7c9026014","io_domain":{"input_subdomain":[{"uri":{"filename":"glytoucan_allacc.txt","uri":"/data/shared/glyds/downloads/glycan_list/05_17_2023/glytoucan_allacc.txt"}},{"uri":{"filename":"glytoucan_archived.txt","uri":"/data/shared/glyds/downloads/glycan_list/05_17_2023/glytoucan_archived.txt"}},{"uri":{"filename":"glytoucan_replaced.txt","uri":"/data/shared/glyds/downloads/glycan_list/05_17_2023/glytoucan_replaced.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_glytoucanidlist.csv","filename":"glycan_glytoucanidlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_glytoucanidlist.stat.csv","filename":"glycan_glytoucanidlist.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:06.220000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000588/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000588/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Reaction Participants (Reactome)","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-07T14:06:11.683031","modified":"2024-05-21T15:11:57.997Z","version":"v-0.0.0"},"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"usability_domain":["The Human Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Homo sapiens [taxid:9606] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"etag":"f30b321514e1f9952851a495b08fa0ad30c39708ab35d95bc3288510f48a15df","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_participants_reactome.csv","filename":"human_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_participants_reactome.stat.csv","filename":"human_protein_participants_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":372,"last_update":"2024-05-21T15:11:57.997137Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000588/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000588/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Reaction Participants (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-07T14:06:11.683031","modified":"2022-09-26T09:08:12.452665","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"68f0c98702ab63bf75f7a60f807f97715696009bc099191b31f175d6bb3dbd38","io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"https:/data.glygen.org/ln2downloads/chebi/07_16_2021/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_participants_reactome.csv","filename":"human_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_participants_reactome.stat.csv","filename":"human_protein_participants_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.426000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000588/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000588/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Reaction Participants (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-07T14:06:11.683031","modified":"2022-09-26T09:08:12.452665","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"5cc3cb24807c510e1d9acd8ab8ca87f1","io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"/data/shared/glyds/downloads/chebi/2023_05_19/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_participants_reactome.csv","filename":"human_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_participants_reactome.stat.csv","filename":"human_protein_participants_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:06.416000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000589/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000589/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Reaction Participants (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-07T14:12:42.192797","modified":"2024-05-17T11:24:05.634Z","version":"v-0.0.0"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"4177a7365c3c8bb8d8899e8faa8b9b3d93589218564c728ca904d11e461c8863","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_participants_rhea.csv","filename":"human_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_participants_rhea.stat.csv","filename":"human_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:05.634701Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000589/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000589/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Reaction Participants (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-07T14:12:42.192797","modified":"2022-09-26T09:08:12.530818","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"ab7a0b5f543ada5bed72deb4f5af3efbab20ac558dc2406d5b890725bcead69d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_participants_rhea.csv","filename":"human_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_participants_rhea.stat.csv","filename":"human_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.765000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000589/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000589/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Reaction Participants (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-07T14:12:42.192797","modified":"2022-09-26T09:08:12.530818","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"84111ba38c334541368cb1dbc0d6ef20","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_participants_rhea.csv","filename":"human_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_participants_rhea.stat.csv","filename":"human_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:06.621000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000590/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000590/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Reaction Participants (Reactome)","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-07T14:15:48.605914","modified":"2024-05-21T15:11:40.921Z","version":"v-0.0.0"},"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Mus musculus [taxid:10090] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"etag":"4c97cf5af47b321d706e4b1ae554a8b4cfd35ce55fad9ab2f17b9862363758a4","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_participants_reactome.csv","filename":"mouse_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_participants_reactome.stat.csv","filename":"mouse_protein_participants_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":373,"last_update":"2024-05-21T15:11:40.921984Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000590/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000590/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Reaction Participants (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-07T14:15:48.605914","modified":"2022-09-26T09:08:12.733442","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"b10748931e0f35c9dc4b0fdb177e22abaa384cdc2fc8402694fbec62734b8290","io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"https:/data.glygen.org/ln2downloads/chebi/07_16_2021/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_participants_reactome.csv","filename":"mouse_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_participants_reactome.stat.csv","filename":"mouse_protein_participants_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.334000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000590/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000590/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Reaction Participants (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-07T14:15:48.605914","modified":"2022-09-26T09:08:12.733442","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"493159543d0c39aa72149b957b30b754","io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"/data/shared/glyds/downloads/chebi/2023_05_19/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_participants_reactome.csv","filename":"mouse_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_participants_reactome.stat.csv","filename":"mouse_protein_participants_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:06.818000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000591/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000591/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"641c319a9cfd6ab159c24eaab4fcd37a864e6f74b6fff3fa6803855211726406","provenance_domain":{"name":"Mouse Reaction Participants (Rhea)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-07T14:19:46.976011","modified":"2025-03-06T15:40:55.988Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Reaction Participants (Rhea) dataset offers detailed information on enzymatic participants involved in chemical and transport reactions specific to Mus musculus [TaxID: 10090]. Rhea is a rigorously curated knowledgebase that catalogs biologically significant reactions and serves as the authoritative standard for enzyme and transporter annotation in UniProtKB. To characterize reaction participants, Rhea leverages the Chemical Entities of Biological Interest (ChEBI) dictionary."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_participants_rhea.csv","filename":"mouse_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_participants_rhea.stat.csv","filename":"mouse_protein_participants_rhea.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":593,"last_update":"2025-03-06T15:40:55.988772Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000591/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000591/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Reaction Participants (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-07T14:19:46.976011","modified":"2022-09-26T09:08:12.750927","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"3c7f1a34fdc41197f68f7dfdb9a36f94f985f09a140f1b3a0c8231ecbfe5ebb4","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_participants_rhea.csv","filename":"mouse_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_participants_rhea.stat.csv","filename":"mouse_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.316000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000591/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000591/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Reaction Participants (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-07T14:19:46.976011","modified":"2022-09-26T09:08:12.750927","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"bf29fa7dbf40b2ae897a4bbedbf13fab","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_participants_rhea.csv","filename":"mouse_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_participants_rhea.stat.csv","filename":"mouse_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:07.026000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000592/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000592/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Rat Reaction Participants (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-07T14:35:34.045437","modified":"2024-05-21T15:11:13.243Z","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"usability_domain":["The Rat Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Rattus norvegicus [taxid:10116] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"etag":"7ff494686a155428f95332c41f889d3cfb709220813fe5af2f4dca32d1c82bc6","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_participants_reactome.csv","filename":"rat_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_participants_reactome.stat.csv","filename":"rat_protein_participants_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":376,"last_update":"2024-05-21T15:11:13.243256Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000592/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000592/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Reaction Participants (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-07T14:35:34.045437","modified":"2022-09-26T09:08:12.474565","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"0a4d8b68b868a35b3bb00f79600c826b351b59d3c63f97c803d56159cd8b79af","io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"https:/data.glygen.org/ln2downloads/chebi/07_16_2021/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_participants_reactome.csv","filename":"rat_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_participants_reactome.stat.csv","filename":"rat_protein_participants_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.418000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000592/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000592/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Reaction Participants (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-07T14:35:34.045437","modified":"2022-09-26T09:08:12.474565","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"bc886d6ea007577770c4a242d2129842","io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"/data/shared/glyds/downloads/chebi/2023_05_19/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_participants_reactome.csv","filename":"rat_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_participants_reactome.stat.csv","filename":"rat_protein_participants_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:07.219000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000593/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000593/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e9d57ad7eba2c50b040a1fe69da14727b768b68dcb5fc1cae42f2ec5bbbdabe9","provenance_domain":{"name":"Rat Reaction Participants (Rhea)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-07T14:36:57.176109","modified":"2025-03-06T15:38:51.344Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Reaction Participants (Rhea) dataset offers detailed information on enzymatic participants involved in chemical and transport reactions specific to Rattus norvegicus [TaxID: 10116]. Rhea is a rigorously curated knowledgebase that catalogs biologically significant reactions and serves as the authoritative standard for enzyme and transporter annotation in UniProtKB. To characterize reaction participants, Rhea leverages the Chemical Entities of Biological Interest (ChEBI) dictionary."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_participants_rhea.csv","filename":"rat_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_participants_rhea.stat.csv","filename":"rat_protein_participants_rhea.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":596,"last_update":"2025-03-06T15:38:51.344742Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000593/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000593/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Reaction Participants (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-07T14:36:57.176109","modified":"2022-09-26T09:08:12.489255","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"6bfa02012ce85eed46bb9a62efd92bceda7ddf955e20ca758b0e1d02b50efd93","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_participants_rhea.csv","filename":"rat_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_participants_rhea.stat.csv","filename":"rat_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.019000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000593/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000593/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Reaction Participants (Rhea)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-07T14:36:57.176109","modified":"2022-09-26T09:08:12.489255","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"94f7c2906af05be1d9c82da17574a5e5","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_participants_rhea.csv","filename":"rat_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_participants_rhea.stat.csv","filename":"rat_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:07.410000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000594/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000594/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Pathways (Reactome)","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T06:14:22.181602","modified":"2024-05-21T15:39:19.176Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Human Pathways (Reactome) dataset contains Homo sapiens [taxid:9606] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"e84f3ef95ccae648500f8a4501240df47b72f8b3fab24b72d4670cde3d9911b3","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_pathways_reactome.csv","filename":"human_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_pathways_reactome.stat.csv","filename":"human_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-05-21T15:39:19.176012Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000594/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000594/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Pathways (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-10-15T06:14:22.181602","modified":"2022-09-26T09:08:12.554511","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_pathways_reactome.csv","filename":"human_protein_pathways_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"294cc7bf75d71b91c40b408383bad934a2b6ed37b30a8fa3db0a0e5a1db289cb","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_pathways_reactome.csv","filename":"human_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_pathways_reactome.stat.csv","filename":"human_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.634000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000594/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000594/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Pathways (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T06:14:22.181602","modified":"2022-09-26T09:08:12.554511","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_pathways_reactome.csv","filename":"human_protein_pathways_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"f80ea2a0bc9edbdc8a4ba53a0f886783","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_pathways_reactome.csv","filename":"human_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_pathways_reactome.stat.csv","filename":"human_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:07.604000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000595/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000595/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Pathways (Reactome)","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T06:17:22.191402","modified":"2024-05-21T15:40:23.225Z","version":"v-0.0.0"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Mouse Pathways (Reactome) dataset contains Mus musculus [taxid:10090] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"da442e6c8e35c339d24513c1c8de870ab1d9e3046206845b0c654bec3f78d4bb","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_pathways_reactome.csv","filename":"mouse_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_pathways_reactome.stat.csv","filename":"mouse_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":362,"last_update":"2024-05-21T15:40:23.225303Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000595/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000595/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Pathways (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T06:17:22.191402","modified":"2022-09-26T09:08:12.617482","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_pathways_reactome.csv","filename":"mouse_protein_pathways_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"9f82900288ec6a29d0781867108d4d02de84cb79035f5e6ec365e632976746b2","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_pathways_reactome.csv","filename":"mouse_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_pathways_reactome.stat.csv","filename":"mouse_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.712000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000595/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000595/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Pathways (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T06:17:22.191402","modified":"2022-09-26T09:08:12.617482","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_pathways_reactome.csv","filename":"mouse_protein_pathways_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"84b5629dd42bdf11d967021ccd19d99b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_pathways_reactome.csv","filename":"mouse_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_pathways_reactome.stat.csv","filename":"mouse_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:07.798000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000596/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000596/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Rat Pathways (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T06:24:07.054558","modified":"2024-05-21T15:41:07.169Z","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Rat Pathways (Reactome) dataset contains Rattus norvegicus [taxid:10116] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"2c9ddc6ba5fbb566bb4742dad9d82e4a77c9bb45ccebaf6977dd3b7eafb689ea","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_pathways_reactome.csv","filename":"rat_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_pathways_reactome.stat.csv","filename":"rat_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":365,"last_update":"2024-05-21T15:41:07.169569Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000596/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000596/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Pathways (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-10-15T06:24:07.054558","modified":"2022-09-26T09:08:12.660888","version":"v-2.0.2"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_pathways_reactome.csv","filename":"rat_protein_pathways_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"3bb8be6dcec868858bb246935d7a6401a8504c1636f2f743f98d37cf8cdd62ee","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_pathways_reactome.csv","filename":"rat_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_pathways_reactome.stat.csv","filename":"rat_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.875000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000596/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000596/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Pathways (Reactome)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T06:24:07.054558","modified":"2022-09-26T09:08:12.660888","version":"v-2.1.1"},"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_pathways_reactome.csv","filename":"rat_protein_pathways_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"etag":"febec50598b8a163c853a4186723cb9d","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_pathways_reactome.csv","filename":"rat_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_pathways_reactome.stat.csv","filename":"rat_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:07.999000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000597/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000597/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T06:33:28.159541","modified":"2024-05-17T11:24:05.962Z","version":"v-0.0.0"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Rhea contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"etag":"54aaa21096b615c051ee7c63bf33345a7bbf98782b4a047aa398ef749e560861","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_rhea.csv","filename":"human_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_rhea.stat.csv","filename":"human_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":246,"last_update":"2024-05-17T11:24:05.962935Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000597/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000597/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-10-15T06:33:28.159541","modified":"2022-09-26T09:08:12.706789","version":"v-2.0.2"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_rhea.csv","filename":"human_protein_xref_rhea.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Rhea contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"etag":"30e29ef3a2d116929976b0edfbef8a2f3632daa134615dd9828ab4d6c5a5be6a","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_rhea.csv","filename":"human_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_rhea.stat.csv","filename":"human_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.386000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000597/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000597/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T06:33:28.159541","modified":"2022-09-26T09:08:12.706789","version":"v-2.1.1"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_rhea.csv","filename":"human_protein_xref_rhea.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Human UniProtKB Xref Rhea contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"etag":"13fdc20ff3b5ba79e17ab77af408fac0","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_rhea.csv","filename":"human_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_rhea.stat.csv","filename":"human_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:08.197000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000598/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000598/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T06:37:18.292686","modified":"2024-05-17T11:24:06.000Z","version":"v-0.0.0"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Rhea contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"etag":"de7b0139f4d9312e14ed93e105c7fdd1e9df1aa508ab34a934a8cead9cd62fee","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_rhea.csv","filename":"mouse_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_rhea.stat.csv","filename":"mouse_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":251,"last_update":"2024-05-17T11:24:06.000125Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000598/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000598/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"created":"2021-10-15T06:37:18.292686","modified":"2022-09-26T09:08:12.579425","version":"v-2.0.2"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_xref_rhea.csv","filename":"mouse_protein_xref_rhea.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Rhea contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"etag":"0585d731a9d82bc0eae4c013c1a200c09540370cfea299a177a137c9128be679","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_rhea.csv","filename":"mouse_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_rhea.stat.csv","filename":"mouse_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.440000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000598/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000598/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T06:37:18.292686","modified":"2022-09-26T09:08:12.579425","version":"v-2.1.1"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_xref_rhea.csv","filename":"mouse_protein_xref_rhea.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Mouse UniProtKB Xref Rhea contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"etag":"822db70a2cbfdef6444fa2a82887f00b","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_rhea.csv","filename":"mouse_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_rhea.stat.csv","filename":"mouse_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:08.392000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000599/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000599/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T06:39:59.122715","modified":"2024-05-17T11:24:06.036Z","version":"v-0.0.0"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat UniProtKB Xref Rhea contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Rhea"],"etag":"9f5c78d73ac6bcdf138127a06b0d20f247558831efa809bd4cf71fc33b1798a8","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_rhea.csv","filename":"rat_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_rhea.stat.csv","filename":"rat_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":253,"last_update":"2024-05-17T11:24:06.036391Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000599/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000599/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T06:39:59.122715","modified":"2022-09-26T09:08:12.587959","version":"v-2.0.2"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_rhea.csv","filename":"rat_protein_xref_rhea.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat UniProtKB Xref Rhea contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Rhea"],"etag":"bdfbf9b16d13e7c6f1cfbfedb8611431c29db37a0278b278ae108deffdbfa744","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_rhea.csv","filename":"rat_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_rhea.stat.csv","filename":"rat_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.144000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000599/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000599/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T06:39:59.122715","modified":"2022-09-26T09:08:12.587959","version":"v-2.1.1"},"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_rhea.csv","filename":"rat_protein_xref_rhea.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The Rat UniProtKB Xref Rhea contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Rhea"],"etag":"c0341a952189977cbdb991d7d0058f71","io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_rhea.csv","filename":"rat_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_rhea.stat.csv","filename":"rat_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:08.585000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000600/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000600/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cb96e9b770758a0b1b26d8f4054e541bfc812f5f7f4df39179237eba24fc7f1b","provenance_domain":{"name":"Glycan NCFG","version":"v-0.0.0","created":"2021-10-15T07:01:02.756996","modified":"2024-05-17T11:24:06.075Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"name":"Richard Cummings","contribution":["contributedBy"],"affiliation":"Harvard Medical School","email":"rcummin1@bidmc.harvard.edu","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["-","The dataset provides evidence for a library of complex multiantennary Asn-linked N-glycans generated by chemo-enzymatic synthesis (PMID:30745240).  The data was contributed by the Richard Cummings Laboratory (NCFG BIDMC Harvard Medical School)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Evidence","NCFG"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_ncfg.csv","filename":"glycan_ncfg.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_ncfg.stat.csv","filename":"glycan_ncfg.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"evidence NCFG","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":245,"last_update":"2024-05-17T11:24:06.075300Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000600/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000600/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"evidence NCFG","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Evidence NCFG","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T07:01:02.756996","modified":"2022-09-26T09:08:12.747894","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Evidence","NCFG"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_evidence_ncfg.csv","filename":"glycan_evidence_ncfg.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"961669fb12b59c71d557f6b6f0ce8310c748680a48f6315e5a775238bcd3c51f","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_evidence_ncfg.csv","uri":"https:/data.glygen.org/ln2downloads/ncfg/09_01_2020/glycan_evidence_ncfg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_evidence_ncfg.csv","filename":"glycan_evidence_ncfg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_evidence_ncfg.stat.csv","filename":"glycan_evidence_ncfg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.569000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000600/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000600/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1f80ba01fb83035953aa927c5e312e85","provenance_domain":{"name":"Glycan NCFG","version":"v-2.1.1","created":"2021-10-15T07:01:02.756996","modified":"2023-03-14T17:03:02.034Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"name":"Richard Cummings","contribution":["contributedBy"],"affiliation":"Harvard Medical School","email":"rcummin1@bidmc.harvard.edu","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["-","The dataset provides evidence for a library of complex multiantennary Asn-linked N-glycans generated by chemo-enzymatic synthesis (PMID:30745240).  The data was contributed by the Richard Cummings Laboratory (NCFG BIDMC Harvard Medical School)."],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Evidence","NCFG"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2downloads/v-2.1.1/09_01_2020/glycan_evidence_ncfg.csv","filename":"glycan_evidence_ncfg.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_ncfg.csv","filename":"glycan_ncfg.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_evidence_ncfg.csv","uri":"/data/shared/glyds/downloads/ncfg/09_01_2020/glycan_evidence_ncfg.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_ncfg.csv","filename":"glycan_ncfg.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_ncfg.stat.csv","filename":"glycan_ncfg.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"evidence NCFG","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:08:21.976000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000601/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000601/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"glytoucan accession history","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Accession History","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T07:03:24.189582","modified":"2024-05-17T11:24:06.115Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","History",""],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"5276bed761e6015960f81fb78d647a748816623667c0ed46f574270c3f9ff6f0","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_glytoucan_accession_history.csv","filename":"glycan_glytoucan_accession_history.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_glytoucan_accession_history.stat.csv","filename":"glycan_glytoucan_accession_history.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1,"last_update":"2024-05-17T11:24:06.115225Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000601/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000601/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"glytoucan accession history","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Accession History","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T07:03:24.189582","modified":"2022-09-26T09:08:12.735177","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","History",""],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_glytoucan_accession_history.csv","filename":"glycan_glytoucan_accession_history.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"d58360b6bdfe89b47d3f7a5c6184bca625eccd6534a481895526595626dbb138","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glygen_retired_accessions.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/glygen_retired_accessions.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_glytoucan_accession_history.csv","filename":"glycan_glytoucan_accession_history.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_glytoucan_accession_history.stat.csv","filename":"glycan_glytoucan_accession_history.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:39.933000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000601/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000601/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"glytoucan accession history","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Accession History","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T07:03:24.189582","modified":"2022-09-26T09:08:12.735177","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","History",""],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_glytoucan_accession_history.csv","filename":"glycan_glytoucan_accession_history.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"8122fad11cbfd2883abcd8cbbbc17b06","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glygen_retired_accessions.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/glygen_retired_accessions.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_glytoucan_accession_history.csv","filename":"glycan_glytoucan_accession_history.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_glytoucan_accession_history.stat.csv","filename":"glycan_glytoucan_accession_history.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:08.905000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000602/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000602/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyTouCan Linkout","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan GlyTouCan Linkout","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T07:06:50.190647","modified":"2024-05-17T11:24:06.157Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyTouCan Linkout"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"cbdbe452a85dfe3ffce9f363f0854095c97813e4857a26a887479629fe516384","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_glytoucan_linkout.csv","filename":"glycan_glytoucan_linkout.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_glytoucan_linkout.stat.csv","filename":"glycan_glytoucan_linkout.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1,"last_update":"2024-05-17T11:24:06.157640Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000602/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000602/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyTouCan Linkout","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan GlyTouCan Linkout","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T07:06:50.190647","modified":"2022-09-26T09:08:12.495919","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyTouCan Linkout"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_glytoucan_accession_history.csv","filename":"glycan_glytoucan_accession_history.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"3d2261684abc137c549c8e38601e2407a4c7e88901c25953c4f1399b69abc55b","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_sequences_wurcs.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_sequences_wurcs.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_glytoucan_linkout.csv","filename":"glycan_glytoucan_linkout.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_glytoucan_linkout.stat.csv","filename":"glycan_glytoucan_linkout.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.179000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000602/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000602/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyTouCan Linkout","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan GlyTouCan Linkout","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T07:06:50.190647","modified":"2022-09-26T09:08:12.495919","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyTouCan Linkout"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_glytoucan_accession_history.csv","filename":"glycan_glytoucan_accession_history.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"df361a3cca5f29011065501d42d7bb05","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_sequences_wurcs.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_sequences_wurcs.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_glytoucan_linkout.csv","filename":"glycan_glytoucan_linkout.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_glytoucan_linkout.stat.csv","filename":"glycan_glytoucan_linkout.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:09.098000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000603/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000603/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Pathway Reactome","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Pathway Reactome","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T07:09:29.335203","modified":"2024-05-17T11:24:06.196Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","Pathway","Reactome"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"f59c82d829ecec5d5cd5399673877d24f9cff9ea552d9110b4689b403fc44e32","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_pathway_reactome.csv","filename":"glycan_pathway_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_pathway_reactome.stat.csv","filename":"glycan_pathway_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1,"last_update":"2024-05-17T11:24:06.196253Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000603/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000603/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Pathway Reactome","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Pathway Reactome","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T07:09:29.335203","modified":"2022-09-26T09:08:12.468986","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","Pathway","Reactome"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_pathway_reactome.csv","filename":"glycan_pathway_reactome.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"06cb59a49d3f4361966aea00f0628260c7cb018d6de1f36dbc3e40af2779a684","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_chebi.csv"}},{"uri":{"filename":"ChEBI2Reactome_PE_Pathway.csv","uri":"https:/data.glygen.org/ln2downloads/reactome/04_08_2021/ChEBI2Reactome_PE_Pathway.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_pathway_reactome.csv","filename":"glycan_pathway_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_pathway_reactome.stat.csv","filename":"glycan_pathway_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.839000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000603/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000603/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Pathway Reactome","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Rattus"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Pathway Reactome","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T07:09:29.335203","modified":"2022-09-26T09:08:12.468986","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","Pathway","Reactome"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_pathway_reactome.csv","filename":"glycan_pathway_reactome.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"ff963b3e84517efa5d09380147acfd06","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_chebi.csv"}},{"uri":{"filename":"ChEBI2Reactome_PE_Pathway.txt","uri":"/data/shared/glyds/downloads/reactome/2023_05_19/ChEBI2Reactome_PE_Pathway.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_pathway_reactome.csv","filename":"glycan_pathway_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_pathway_reactome.stat.csv","filename":"glycan_pathway_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:09.293000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000604/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000604/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Xref Reactome","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Reactome","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T07:11:59.137251","modified":"2024-05-17T11:24:06.236Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","Xref Reactome"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"8da1ddd5369ebfafd2d50edf92da5436d8f890356f7076dd328e19e70178e276","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_reactome.csv","filename":"glycan_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_reactome.stat.csv","filename":"glycan_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1,"last_update":"2024-05-17T11:24:06.236321Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000604/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000604/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Xref Reactome","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Reactome","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T07:11:59.137251","modified":"2022-09-26T09:08:12.627273","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","Xref Reactome"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_reactome.csv","filename":"glycan_xref_reactome.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"44169c45420a32c4c8e3ff48847b8baaf3a44128b9a8ef7e4988dc367227c3a1","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_chebi.csv"}},{"uri":{"filename":"ChEBI2Reactome_PE_Pathway.csv","uri":"https:/data.glygen.org/ln2downloads/reactome/04_08_2021/ChEBI2Reactome_PE_Pathway.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_reactome.csv","filename":"glycan_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_reactome.stat.csv","filename":"glycan_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.817000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000604/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000604/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Xref Reactome","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Reactome","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T07:11:59.137251","modified":"2022-09-26T09:08:12.627273","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","Xref Reactome"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_reactome.csv","filename":"glycan_xref_reactome.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"b7dc84bf15eedd6593db6aa85ad8e152","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_chebi.csv"}},{"uri":{"filename":"ChEBI2Reactome_PE_Pathway.txt","uri":"/data/shared/glyds/downloads/reactome/2023_05_19/ChEBI2Reactome_PE_Pathway.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_reactome.csv","filename":"glycan_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_reactome.stat.csv","filename":"glycan_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:09.493000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000605/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000605/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a875a804ca23385c6115b2af4a3f1cd41e17316a553c34b447074ee705aac875","provenance_domain":{"name":"Glycan Xref Rhea","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T07:13:00.687378","modified":"2025-03-06T15:30:33.211Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Glycan Xref (Rhea) dataset offers detailed information on enzymatic reaction IDs involved in chemical and transport reactions specific to Dictyostelium discoideum [TaxID: 44689]. Rhea is a rigorously curated knowledgebase that catalogs biologically significant reactions and serves as the authoritative standard for enzyme and transporter annotation in UniProtKB. To characterize reaction participants, Rhea leverages the Chemical Entities of Biological Interest (ChEBI) dictionary. "],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[]}],"keywords":["Glycan","Xref Rhea"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_rhea.csv","filename":"glycan_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_rhea.stat.csv","filename":"glycan_xref_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Xref Rhea","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":596,"last_update":"2025-03-06T15:30:33.211155Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000605/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000605/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Xref Rhea","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T07:13:00.687378","modified":"2022-09-26T09:08:12.551431","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","Xref Rhea"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_rhea.csv","filename":"glycan_xref_rhea.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"3f2ccd5ab88cf0b25bd6fefb5be4a3d0bf23251dfdfeb0cddcde99c147f90677","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_chebi.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_rhea.csv","filename":"glycan_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_rhea.stat.csv","filename":"glycan_xref_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.203000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000605/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000605/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Xref Rhea","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Rhea","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T07:13:00.687378","modified":"2022-09-26T09:08:12.551431","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","Xref Rhea"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_rhea.csv","filename":"glycan_xref_rhea.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"c37f11060c223b156e12a5db40795e0a","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_chebi.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_chebi.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_rhea.csv","filename":"glycan_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_rhea.stat.csv","filename":"glycan_xref_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:09.676000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000606/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000606/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Top Authors","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Top Authors","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T07:54:45.197512","modified":"2024-05-17T11:24:06.312Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","Top Authors"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"cdf8f3b32de8c3d62f9ad7acdbde7a881f44b7d92a656d6b9458a94db4aff3b8","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_top_authors.csv","filename":"glycan_top_authors.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_top_authors.stat.csv","filename":"glycan_top_authors.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1,"last_update":"2024-05-17T11:24:06.312816Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000606/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000606/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Top Authors","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Top Authors","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T07:54:45.197512","modified":"2022-09-26T09:08:12.702087","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","Top Authors"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_top_authors.csv","filename":"glycan_top_authors.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"55f9bb7659fcbf4c30e39176e46caf3167b223d6a6339272150aaa8fddfbe679","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_citations_glycomotif.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_glycomotif.csv"}},{"uri":{"filename":"glycan_citations_glytoucan.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_citations_glytoucan.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_top_authors.csv","filename":"glycan_top_authors.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_top_authors.stat.csv","filename":"glycan_top_authors.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:41.735000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000606/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000606/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Top Authors","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Top Authors","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T07:54:45.197512","modified":"2022-09-26T09:08:12.702087","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","Top Authors"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_top_authors.csv","filename":"glycan_top_authors.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["-"],"etag":"83559ae51fca116f925f2c495a5e8fbe","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_citations_biomarkers.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_biomarkers.csv"}},{"uri":{"filename":"glycan_citations_glytoucan.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_glytoucan.csv"}},{"uri":{"filename":"glycan_citations_motif.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_motif.csv"}},{"uri":{"filename":"glycan_citations_ncfg.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_ncfg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_top_authors.csv","filename":"glycan_top_authors.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_top_authors.stat.csv","filename":"glycan_top_authors.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:09.875000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000607/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000607/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c00cdbd6d5dd9fb75cfea854f269ff47aedc0181b6a540952a2be2e0893a8133","provenance_domain":{"name":"Human Proteoform Phosphorylation Citations (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T08:00:04.645468","modified":"2025-10-09T14:20:58.736Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Proteoform Phosphorylation Citations (UniProtKB) dataset contains human [taxid:9606] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":336,"last_update":"2025-10-09T14:20:58.736954Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000607/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000607/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Proteoform Phosphorylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T08:00:04.645468","modified":"2022-09-26T09:08:12.664456","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"45750838564b329d0e5e9a745566ba01ea346a00865e35c0ed74f2358866da3d","io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"human_proteoform_citations_phosphorylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_citations_phosphorylation_uniprotkb.stat.csv","filename":"human_proteoform_citations_phosphorylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000607/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000607/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c078ea0450dc8d7f4808f55d6cf8b0a2","provenance_domain":{"name":"Human Proteoform Phosphorylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-10-15T08:00:04.645468","modified":"2023-03-14T17:04:43.841Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:10.068000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000608/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000608/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"50825d7735ee50a0e4c6d89961ea512d89816c8af448edbde9d62ed265239f74","provenance_domain":{"name":"Mouse Proteoform Phosphorylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-10-15T08:01:56.010001","modified":"2025-10-09T14:25:10.690Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Proteoform Phosphorylation Citations (UniProtKB) dataset contains Mus musculus [taxid:10090] publication information of phosphorylated glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2025-10-09T14:25:10.690607Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000608/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000608/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Mouse Proteoform Phosphorylation Citations (UniProtKB)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T08:01:56.010001","modified":"2022-09-26T09:08:12.589112","version":"v-2.0.2"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"26df589ea0d871524c056e73889c62892c9f05437e4b083ac5f5d9c89a673061","io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"mouse_proteoform_citations_phosphorylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_phosphorylation_uniprotkb.stat.csv","filename":"mouse_proteoform_citations_phosphorylation_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.504000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000608/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000608/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6ebfe49c7ad24dc18f76c3109e10074b","provenance_domain":{"name":"Mouse Proteoform Phosphorylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-10-15T08:01:56.010001","modified":"2023-03-14T17:05:22.996Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:10.255000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000609/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000609/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c6938948f2922aca41db7cace8dce639193f4ef543eb82612dc1892f684b5d11","provenance_domain":{"name":"Rat Proteoform Phosphorylation Citations (UniProtKB)","version":"v-0.0.0","created":"2021-10-15T08:03:13.531431","modified":"2025-10-09T14:27:09.947Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Proteoform Phosphorylation Citations (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] publication information of phosphorylated glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":367,"last_update":"2025-10-09T14:27:09.947931Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000609/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"rat_proteoform_citations_phosphorylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_phosphorylation_uniprotkb.stat.csv","filename":"rat_proteoform_citations_phosphorylation_uniprotkb.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"","created":"2021-10-15T08:03:13.531431","modified":"2022-09-26T09:08:12.578486","version":"v-2.0.2","name":"Rat Proteoform Phosphorylation Citations (UniProtKB)"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"object_id":"https://biocomputeobject.org/GLY_000609/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"667a087531be734c608a71ece687edf8bbdba7970481100a613f217317bec41c","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.917000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000609/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000609/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"aa2216643dede260678fa12568bd7fe2","provenance_domain":{"name":"Rat Proteoform Phosphorylation Citations (UniProtKB)","version":"v-2.1.1","created":"2021-10-15T08:03:13.531431","modified":"2023-03-14T16:27:29.522Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":[],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"platform":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:01.535000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000610/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000610/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a60e3dd1d8f0c5ba98402c1d231f36c4bad67800cd988947124d1978707b2846","provenance_domain":{"name":"Human PRO Proteoform","version":"v-0.0.0","created":"2021-10-15T14:43:28.584379","modified":"2025-10-09T14:28:59.587Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pro_proteoform.csv","filename":"human_protein_xref_pro_proteoform.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_pro_proteoform.stat.csv","filename":"human_protein_xref_pro_proteoform.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRO Proteoform","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2025-10-09T14:28:59.587398Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000610/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000610/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRO Proteoform","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human PRO Proteoform","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T14:43:28.584379","modified":"2022-09-26T09:08:12.711417","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"b8c2fcda56134c4004c321bf6284e02f8497d665ad9388e3fd0d13887c5ffbfe","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"https:/data.glygen.org/ln2downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pro_proteoform.csv","filename":"human_protein_xref_pro_proteoform.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_pro_proteoform.stat.csv","filename":"human_protein_xref_pro_proteoform.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.024000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000610/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000610/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRO Proteoform","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human PRO Proteoform","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T14:43:28.584379","modified":"2022-09-26T09:08:12.711417","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"e3bf6025df10eedecc769c4f2534e2eb","io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"/data/shared/glyds/downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pro_proteoform.csv","filename":"human_protein_xref_pro_proteoform.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pro_proteoform.stat.csv","filename":"human_protein_xref_pro_proteoform.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:10.576000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000611/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000611/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5a06e198f4a0692617b7e7ff4e789373dda97df5dcc63cb4b5cbaa0dea0b9d02","provenance_domain":{"name":"Human Glycosylation Sites UniCarbKB Glycomics Study","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T14:54:25.104978","modified":"2025-03-03T16:12:01.436Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniCarbKB Glycomics Study contains Homo sapiens [taxid:9606] glycan tissue expression data. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen. UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan","glycomics study"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites glycomics study","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":413,"last_update":"2025-03-03T16:12:01.436367Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000611/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000611/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites glycomics study","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites UniCarbKB Glycomics Study","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T14:54:25.104978","modified":"2022-09-26T09:08:12.654213","version":"v-2.0.2"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan","glycomics study"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[""],"etag":"6817e2ac2f0ed84111702c2115ca69486a7988dbba2d8fae8b03bd18485af856","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:26.601000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000611/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000611/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites glycomics study","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites UniCarbKB Glycomics Study","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T14:54:25.104978","modified":"2022-09-26T09:08:12.654213","version":"v-2.1.1"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan","glycomics study"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[""],"etag":"4661bfc812a61be48cc31abbd278675f","io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:10.772000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000612/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000612/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Glycosylation Sites (Literature)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T15:07:06.347029","modified":"2024-05-17T11:24:06.557Z","version":"v-0.0.0"},"description_domain":{"keywords":["glycosylation","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[""],"etag":"c27f7c59a86585d66e294158c2a79a95541cbe1b764bd2063ca2fc5a5d588ef5","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:06.557610Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000612/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000612/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Glycosylation Sites (Literature)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T15:07:06.347029","modified":"2022-09-26T09:08:12.599466","version":"v-2.0.2"},"description_domain":{"keywords":["glycosylation","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[""],"etag":"44db3e50e385d248f21f047408351962b5f356f5b8683c34777bd8a29b07d21f","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_sites_lit_23090970_s2.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_23090970_s2.csv"}},{"uri":{"filename":"glycosylation_sites_lit_23090970_s5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_23090970_s5.csv"}},{"uri":{"filename":"glycosylation_sites_lit_24190977_s5.cs","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_24190977_s5.cs"}},{"uri":{"filename":"glycosylation_sites_lit_x_sx.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/glycosylation_sites_lit_x_sx.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.610000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000612/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000612/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Glycosylation Sites (Literature)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T15:07:06.347029","modified":"2022-09-26T09:08:12.599466","version":"v-2.1.1"},"description_domain":{"keywords":["glycosylation","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[""],"etag":"54194291272e9441526e236968bcb52d","io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_sites_lit_23090970_s2.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_23090970_s2.csv"}},{"uri":{"filename":"glycosylation_sites_lit_23090970_s5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_23090970_s5.csv"}},{"uri":{"filename":"glycosylation_sites_lit_24190977_s5.cs","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_24190977_s5.cs"}},{"uri":{"filename":"glycosylation_sites_lit_x_sx.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/glycosylation_sites_lit_x_sx.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:10.962000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000613/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000613/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9f926908c2f5aa52ae1665fabaa15e2ba9287b7b1eba7954feae272024656e73","provenance_domain":{"name":"SARS-CoV2 Protein Names (NCBI RefSeq)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T15:12:11.510967","modified":"2024-12-10T19:29:45.784Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2) Protein Names (NCBI RefSeq) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_proteinnames_refseq.csv","filename":"sarscov2_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_proteinnames_refseq.stat.csv","filename":"sarscov2_protein_proteinnames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":391,"last_update":"2024-12-10T19:29:45.784206Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000613/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000613/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T15:12:11.510967","modified":"2022-09-26T09:08:12.563488","version":"v-2.0.2"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_info_refseq.csv","filename":"sarscov2_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2) Protein Names (NCBI RefSeq) dataset contains sarscov2 [taxid:2697049] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"99929e9e6bdff481885d6bf65c20a79b38193f65b9df294cbff9ccc20080a847","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_proteinnames_refseq.csv","filename":"sarscov2_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_proteinnames_refseq.stat.csv","filename":"sarscov2_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.819000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000613/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000613/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Names (NCBI RefSeq)","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T15:12:11.510967","modified":"2022-09-26T09:08:12.563488","version":"v-2.1.1"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_info_refseq.csv","filename":"sarscov2_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2) Protein Names (NCBI RefSeq) dataset contains sarscov2 [taxid:2697049] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"etag":"519183ff9f4bf3828266ba878bcb0732","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_proteinnames_refseq.csv","filename":"sarscov2_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_proteinnames_refseq.stat.csv","filename":"sarscov2_protein_proteinnames_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:11.142000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000614/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000614/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 NCBI Protein Linkouts","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T15:17:10.443738","modified":"2024-05-21T15:52:34.278Z","version":"v-0.0.0"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) NCBI Protein Linkouts contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"etag":"e62b346746b91ee526bdb7d03613d23a81d7b2233c1b31a11eac20d8d1e1fd12","io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_ncbi_linkouts.csv","filename":"sarscov1_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_protein_ncbi_linkouts.stat.csv","filename":"sarscov1_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":319,"last_update":"2024-05-21T15:52:34.278089Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000614/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000614/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 NCBI Protein Linkouts","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T15:17:10.443738","modified":"2022-09-26T09:08:12.484903","version":"v-2.0.2"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_ncbi_linkouts.csv","filename":"sarscov1_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) NCBI Protein Linkouts contains sarscov1 [taxid:694009] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"f9f84de3bb8f8f7cd6f9e9ca841fba6761af7819822198a934826a13994b2dec","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_ncbi_linkouts.csv","filename":"sarscov1_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_ncbi_linkouts.stat.csv","filename":"sarscov1_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.461000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000614/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000614/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 NCBI Protein Linkouts","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T15:17:10.443738","modified":"2022-09-26T09:08:12.484903","version":"v-2.1.1"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_ncbi_linkouts.csv","filename":"sarscov1_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) NCBI Protein Linkouts contains sarscov1 [taxid:694009] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"d5538ecb4e135b08fabc6f79fa44080d","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov1_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_ncbi_linkouts.csv","filename":"sarscov1_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_ncbi_linkouts.stat.csv","filename":"sarscov1_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:11.337000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000615/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000615/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7b99699e01509c17f2a917d6e8ce33ef75c93da2d1c9fec34a1796d200103fd7","provenance_domain":{"name":"SARS-CoV2 NCBI Protein Linkouts","version":"v-0.0.0","created":"2021-10-15T15:18:43.701633","modified":"2024-05-21T15:52:51.805Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) NCBI Protein Linkouts contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_ncbi_linkouts.csv","filename":"sarscov2_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_ncbi_linkouts.stat.csv","filename":"sarscov2_protein_ncbi_linkouts.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-21T15:52:51.805344Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000615/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000615/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"The SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 NCBI Protein Linkouts","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T15:18:43.701633","modified":"2022-09-26T09:08:12.483008","version":"v-2.0.2"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_protein_ncbi_linkouts.csv","filename":"sarscov2_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) NCBI Protein Linkouts contains sarscov2 [taxid:2697049] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"etag":"f8fe2fefbdf26596ceb4693304d65f996af23f2e6a8ec74916ce33f52a7a8d93","io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_ncbi_linkouts.csv","filename":"sarscov2_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_ncbi_linkouts.stat.csv","filename":"sarscov2_protein_ncbi_linkouts.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.801000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000615/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000615/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"48c50ec95898416bc988a4a84af70c14","provenance_domain":{"name":"SARS-CoV2 NCBI Protein Linkouts","version":"v-2.1.1","created":"2021-10-15T15:18:43.701633","modified":"2023-03-31T18:52:18.869Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) NCBI Protein Linkouts contains sarscov2 [taxid:2697049] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/sarscov2_protein_ncbi_linkouts.csv","filename":"sarscov2_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"sarscov2_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_ncbi_linkouts.csv","filename":"sarscov2_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_ncbi_linkouts.stat.csv","filename":"sarscov2_protein_ncbi_linkouts.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:11.518000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000617/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000617/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Mutations Loss of Glycosylation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Cancer Mutation Loss of Glycosylation","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2021-10-15T15:32:16.971706","modified":"2024-05-17T11:24:06.720Z","version":"v-0.0.0"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"5265165d9ecb7c2085c239c96ef6a60146256530d0f3e0287a8e3b7cdb473a9d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_cancer_glycosylation_loss.csv","filename":"human_protein_mutation_cancer_glycosylation_loss.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_mutation_cancer_glycosylation_loss.stat.csv","filename":"human_protein_mutation_cancer_glycosylation_loss.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:06.720706Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000617/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000617/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Mutations Loss of Glycosylation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Cancer Mutation Loss of Glycosylation","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T15:32:16.971706","modified":"2022-09-26T09:08:12.730456","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"d5585a4950e31b79f86abb4121b435cc6352504583e974cc0466ecb202cb5314","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_cancer.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer_glycosylation_loss.csv","filename":"human_protein_mutation_cancer_glycosylation_loss.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_mutation_cancer_glycosylation_loss.stat.csv","filename":"human_protein_mutation_cancer_glycosylation_loss.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.269000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000617/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000617/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Mutations Loss of Glycosylation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"","name":"Human Cancer Mutation Loss of Glycosylation","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T15:32:16.971706","modified":"2022-09-26T09:08:12.730456","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"c306a1187942c94c4f2358a2128d3c0c","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"human_protein_mutation_cancer.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer_glycosylation_loss.csv","filename":"human_protein_mutation_cancer_glycosylation_loss.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_cancer_glycosylation_loss.stat.csv","filename":"human_protein_mutation_cancer_glycosylation_loss.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:11.702000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000618/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000618/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1fc66becce239089a77e8e5f831fb66217fbf95779bafca06379c0e23bb0b684","provenance_domain":{"name":"Mouse Germline Mutation Glycoeffect","version":"v-0.0.0","license":"The George Washington University","created":"2021-10-15T15:38:41.625772","modified":"2025-03-11T20:34:25.116Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Germline Mutation GlycoEffect Dataset was derived from the Germline Mutation Dataset provided by the European Bioinformatics Institute (EBI) and dbSNP for Mus musculus [TaxID: 10090]. This dataset is processed from the Germline Mutation Dataset and is useful in context of glycosylation. The dataset, for a given germline mutation site, indicates whether the protein with the germline SNV is a known glycoprotein. Additionally, it provides reference and altered motifs for the mutated glycosylated site and assesses the impact of the SNV on glycosylation. The observed effects include the loss of known O- and N-glycosites and the gain of an N-sequon, which may introduce a new N-glycosylation site. The following headers have been added as part of this analysis: is_known_glycoprotein, motif_start, ref_motif, alt_motif, and effect."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_mutation_germline_glycoeffect.csv","filename":"mouse_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_mutation_germline_glycoeffect.stat.csv","filename":"mouse_protein_mutation_germline_glycoeffect.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutation Glycoeffect","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1016,"last_update":"2025-03-11T20:34:25.116464Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000618/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000618/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutation Glycoeffect","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"The George Washington University","name":"Mouse Germline Mutation Glycoeffect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T15:38:41.625772","modified":"2022-09-26T09:08:12.529178","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"44f55def369b7266d61e4703cfa03aad7266e1dcb7eacdf5a166250aaa13c151","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"mouse_protein_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_mutation_germline.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_mutation_germline_glycoeffect.csv","filename":"mouse_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_mutation_germline_glycoeffect.stat.csv","filename":"mouse_protein_mutation_germline_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.837000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000618/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000618/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutation Glycoeffect","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"The George Washington University","name":"Mouse Germline Mutation Glycoeffect","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T15:38:41.625772","modified":"2022-09-26T09:08:12.529178","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"9a3648b3caa984e10a9aa9f8efa98268","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"mouse_protein_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_mutation_germline.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_mutation_germline_glycoeffect.csv","filename":"mouse_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_mutation_germline_glycoeffect.stat.csv","filename":"mouse_protein_mutation_germline_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:11.891000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000619/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000619/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5449da055bec5e136d920de89a4fd15a15f4c94e9f31c170ff476e3a3c164c9f","provenance_domain":{"name":"Rat Germline Mutation Glycoeffect","version":"v-0.0.0","license":"The George Washington University","created":"2021-10-15T15:41:22.561828","modified":"2025-03-11T20:36:07.761Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Germline Mutation GlycoEffect Dataset was derived from the Germline Mutation Dataset provided by the European Bioinformatics Institute (EBI) and dbSNP for Rattus norvegicus  [TaxID: 10116]. This dataset is processed from the Germline Mutation Dataset and is useful in context of glycosylation. The dataset, for a given germline mutation site, indicates whether the protein with the germline SNV is a known glycoprotein. Additionally, it provides reference and altered motifs for the mutated glycosylated site and assesses the impact of the SNV on glycosylation. The observed effects include the loss of known O- and N-glycosites and the gain of an N-sequon, which may introduce a new N-glycosylation site. The following headers have been added as part of this analysis: is_known_glycoprotein, motif_start, ref_motif, alt_motif, and effect."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_mutation_germline_glycoeffect.csv","filename":"rat_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_mutation_germline_glycoeffect.stat.csv","filename":"rat_protein_mutation_germline_glycoeffect.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutation Glycoeffect","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1021,"last_update":"2025-03-11T20:36:07.761621Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000619/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000619/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutation Glycoeffect","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"The George Washington University","name":"Rat Germline Mutation Glycoeffect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"created":"2021-10-15T15:41:22.561828","modified":"2022-09-26T09:08:12.456398","version":"v-2.0.2"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"338ffadac6f91515eff92daa6ee10644e602919bb5b28a3ceb606f7cce95cb40","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"rat_protein_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_mutation_germline.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_mutation_germline_glycoeffect.csv","filename":"rat_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_mutation_germline_glycoeffect.stat.csv","filename":"rat_protein_mutation_germline_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.820000Z","access_count":54},{"object_id":"https://biocomputeobject.org/GLY_000619/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000619/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutation Glycoeffect","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"The George Washington University","name":"Rat Germline Mutation Glycoeffect","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2021-10-15T15:41:22.561828","modified":"2022-09-26T09:08:12.456398","version":"v-2.1.1"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"etag":"58c5e2272f52a9ccc9d020ea4a5c0bb0","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"rat_protein_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_mutation_germline.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"aadict.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_mutation_germline_glycoeffect.csv","filename":"rat_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_mutation_germline_glycoeffect.stat.csv","filename":"rat_protein_mutation_germline_glycoeffect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:12.083000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000620/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000620/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Dictionary cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Structure Dictionary","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"created":"2022-01-06T12:10:49.966404","modified":"2024-05-17T11:24:06.837Z","version":"v-0.0.0"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Structure Dictionary","Cross-references","Motif"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the associated PMIDs for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to the Glycan Dictionary Accessions for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY000281). Source database: https://wiki.glygen.org/index.php/Glycan_structure_dictionary"],"etag":"ca8423a42a45d91fe3dea56d6b2f7deb662d6c9511509e06916660289a63824d","io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_dictionary.csv","filename":"glycan_xref_dictionary.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_xref_dictionary.stat.csv","filename":"glycan_xref_dictionary.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":323,"last_update":"2024-05-17T11:24:06.837160Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000620/v-2.0.2","contents":{"object_id":"https://biocomputeobject.org/GLY_000620/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Dictionary cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Structure Dictionary","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2022-01-06T12:10:49.966404","modified":"2022-09-26T09:08:12.760740","version":"v-2.0.2"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Structure Dictionary","Cross-references","Motif"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2downloads/v-2.0.2/12_08_2021/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_xref_dictionary.csv","filename":"glycan_xref_dictionary.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the associated PMIDs for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to the Glycan Dictionary Accessions for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY000281). Source database: https://wiki.glygen.org/index.php/Glycan_structure_dictionary"],"etag":"c4831063fb61227180c1becda1d504c8adb924962da1c5680bb6fca3a3ce43b4","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_dictionary.csv","uri":"https:/data.glygen.org/ln2downloads/glycan_dictionary/12_08_2021/glycan_dictionary.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_dictionary.csv","filename":"glycan_xref_dictionary.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_dictionary.stat.csv","filename":"glycan_xref_dictionary.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.338000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000620/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000620/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Dictionary cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"}]}}],"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Structure Dictionary","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"created":"2022-01-06T12:10:49.966404","modified":"2022-09-26T09:08:12.760740","version":"v-2.1.1"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Structure Dictionary","Cross-references","Motif"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2downloads/v-2.1.1/12_08_2021/glycan_dictionary.csv","filename":"glycan_dictionary.csv"}],"output_list":[{"uri":"http://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_xref_dictionary.csv","filename":"glycan_xref_dictionary.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the associated PMIDs for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["The dataset provides cross-references to the Glycan Dictionary Accessions for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY000281). Source database: https://wiki.glygen.org/index.php/Glycan_structure_dictionary"],"etag":"e68400cc8fb04a0fbcc52e30b199c33d","io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_dictionary.csv","uri":"/data/shared/glyds/downloads/glycan_dictionary/03_03_2023/glycan_dictionary.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_dictionary.csv","filename":"glycan_xref_dictionary.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_dictionary.stat.csv","filename":"glycan_xref_dictionary.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:12.271000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000621/DRAFT","contents":{"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_monosaccharide_composition_advanced.csv","filename":"glycan_monosaccharide_composition_advanced.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_monosaccharide_composition_advanced.stat.csv","filename":"glycan_monosaccharide_composition_advanced.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-10T15:38:14.531948","modified":"2024-05-17T11:24:06.875Z","version":"v-0.0.0","name":"Glycan monosaccharide advanced compositions"},"description_domain":{"keywords":["Glycan","GlyTouCan accession","Monosaccharide composition"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"object_id":"https://biocomputeobject.org/GLY_000621/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b723f8cfc05b97c08c1ad758d9f6fb4a6a83a3960dcc0a7ad31af223f03134b1","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":460,"last_update":"2024-05-17T11:24:06.875696Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000621/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocounts.tsv","uri":"https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/monocounts.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_monosaccharide_composition_advanced.csv","filename":"glycan_monosaccharide_composition_advanced.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_monosaccharide_composition_advanced.stat.csv","filename":"glycan_monosaccharide_composition_advanced.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":""}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-10T15:38:14.531948","modified":"2022-09-26T09:08:12.723112","version":"v-2.0.2","name":"Glycan monosaccharide advanced compositions"},"description_domain":{"keywords":["Glycan","GlyTouCan accession","Monosaccharide composition"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2downloads/glytoucan/v-2.0.2/export/monocounts.tsv","filename":"monocounts.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/reviewed/glycan_monosaccharide_composition_advanced.csv","filename":"glycan_monosaccharide_composition_advanced.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"object_id":"https://biocomputeobject.org/GLY_000621/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"76ca701348ea7f99b8146262e12abf64f8c973a34276b7564b900b158a0ddc58","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.486000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000621/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"monocounts.tsv","uri":"/data/shared/glyds/downloads/glytoucan/gtc_05_16_2023/export/monocounts.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_monosaccharide_composition_advanced.csv","filename":"glycan_monosaccharide_composition_advanced.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_monosaccharide_composition_advanced.stat.csv","filename":"glycan_monosaccharide_composition_advanced.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-10T15:38:14.531948","modified":"2022-09-26T09:08:12.723112","version":"v-2.1.1","name":"Glycan monosaccharide advanced compositions"},"description_domain":{"keywords":["Glycan","GlyTouCan accession","Monosaccharide composition"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/monocounts.tsv","filename":"monocounts.tsv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/reviewed/glycan_monosaccharide_composition_advanced.csv","filename":"glycan_monosaccharide_composition_advanced.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"object_id":"https://biocomputeobject.org/GLY_000621/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3ad4dc9ca74eb11ad1eb30661785ba43","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:12.465000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000622/DRAFT","contents":{"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_ncbi_pubmed_linkouts_one.csv","filename":"protein_ncbi_pubmed_linkouts_one.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_ncbi_pubmed_linkouts_two.csv","filename":"protein_ncbi_pubmed_linkouts_two.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_ncbi_pubmed_linkouts_three.csv","filename":"protein_ncbi_pubmed_linkouts_three.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_ncbi_pubmed_linkouts_one.stat.csv","filename":"protein_ncbi_pubmed_linkouts_one.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_ncbi_pubmed_linkouts_two.stat.csv","filename":"protein_ncbi_pubmed_linkouts_two.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_ncbi_pubmed_linkouts_three.stat.csv","filename":"protein_ncbi_pubmed_linkouts_three.stat.csv"}}]},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI PubMed Linkout","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae s288c"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H77)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Gallus gallus"}]}}],"provenance_domain":{"contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-28T16:49:07.908809","modified":"2024-06-03T22:51:40.867Z","version":"v-0.0.0","name":"NCBI PubMed LinkOuts"},"description_domain":{"keywords":["NCBI PubMed","LinkOut","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the PubMed IDs from the input files associated with proteins and glycans in GlyGen and generates publication detail page URLs for corresponding proteins and glycans. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset that is split into three datasets"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["This dataset contains NCBI PubMed IDs associated with all of GlyGen's proteins and glycans with their corresponding GlyGen publication detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into three files."],"object_id":"https://biocomputeobject.org/GLY_000622/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8676d2050e3fed4582b1f189db64929cacd1f922c59abe55c03e3d0ad4e2f5fb"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2024-06-03T22:51:40.867854Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000622/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"human_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_reactome.csv"}},{"uri":{"filename":"human_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_refseq.csv"}},{"uri":{"filename":"human_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_refseq.csv"}},{"uri":{"filename":"mouse_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_refseq.csv"}},{"uri":{"filename":"rat_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"human_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_reactome.csv"}},{"uri":{"filename":"human_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_refseq.csv"}},{"uri":{"filename":"human_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_refseq.csv"}},{"uri":{"filename":"mouse_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_refseq.csv"}},{"uri":{"filename":"rat_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"human_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_reactome.csv"}},{"uri":{"filename":"human_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_refseq.csv"}},{"uri":{"filename":"human_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_refseq.csv"}},{"uri":{"filename":"mouse_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_refseq.csv"}},{"uri":{"filename":"rat_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_citations_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_one.csv","filename":"protein_ncbi_pubmed_linkouts_one.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_two.csv","filename":"protein_ncbi_pubmed_linkouts_two.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_three.csv","filename":"protein_ncbi_pubmed_linkouts_three.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_one.stat.csv","filename":"protein_ncbi_pubmed_linkouts_one.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_two.stat.csv","filename":"protein_ncbi_pubmed_linkouts_two.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_three.stat.csv","filename":"protein_ncbi_pubmed_linkouts_three.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}],"provenance_domain":{"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-28T16:49:07.908809","modified":"2022-03-29T12:20:53.052989","version":"v-2.0.2","name":"NCBI PubMed LinkOuts"},"description_domain":{"keywords":["NCBI PubMed","LinkOut","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/glycan_citations_glycomotif.csv","filename":"glycan_citations_glycomotif.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycation_uniprotkb.csv","filename":"human_proteoform_citations_glycation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_glyconnect.csv","filename":"human_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_harvard.csv","filename":"human_proteoform_citations_glycosylation_harvard.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature.csv","filename":"human_proteoform_citations_glycosylation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_literature_mining.csv","filename":"human_proteoform_citations_glycosylation_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"human_proteoform_citations_glycosylation_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_tyr_o_linked.csv","filename":"human_proteoform_citations_glycosylation_tyr_o_linked.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_unicarbkb.csv","filename":"human_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_glycosylation_uniprotkb.csv","filename":"human_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_phosphorylation_iptmnet.csv","filename":"human_proteoform_citations_phosphorylation_iptmnet.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"human_proteoform_citations_phosphorylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_glyconnect.csv","filename":"mouse_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_literature_mining.csv","filename":"mouse_proteoform_citations_glycosylation_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_unicarbkb.csv","filename":"mouse_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_uniprotkb.csv","filename":"mouse_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_citations_phosphorylation_iptmnet.csv","filename":"mouse_proteoform_citations_phosphorylation_iptmnet.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/v-1.12.1reviewed/mouse_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"mouse_proteoform_citations_phosphorylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_citations_glycation_uniprotkb.csv","filename":"rat_proteoform_citations_glycation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_glyconnect.csv","filename":"rat_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_literature_mining.csv","filename":"rat_proteoform_citations_glycosylation_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_unicarbkb.csv","filename":"rat_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_uniprotkb.csv","filename":"rat_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_citations_phosphorylation_iptmnet.csv","filename":"rat_proteoform_citations_phosphorylation_iptmnet.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"rat_proteoform_citations_phosphorylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_literature.csv","filename":"sarscov1_proteoform_citations_glycosylation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_uniprotkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_glyconnect.csv","filename":"sarscov2_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_unicarbkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov2_proteoform_citations_glycosylation_uniprotkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1a_proteoform_citations_glycosylation_literature.csv","filename":"hcv1a_proteoform_citations_glycosylation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1a_proteoform_citations_glycosylation_uniprotkb.csv","filename":"hcv1a_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1b_proteoform_citations_glycosylation_uniprotkb.csv","filename":"hcv1b_proteoform_citations_glycosylation_uniprotkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_one.csv","filename":"protein_ncbi_pubmed_linkouts_one.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_two.csv","filename":"protein_ncbi_pubmed_linkouts_two.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/protein_ncbi_pubmed_linkouts_three.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-1.12.1/reviewed/protein_ncbi_pubmed_linkouts_three.csv"}],"prerequisite":[],"description":"The script loads the PubMed IDs from the input files associated with proteins and glycans in GlyGen and generates publication detail page URLs for corresponding proteins and glycans. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset that is split into three datasets"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["This dataset contains NCBI PubMed IDs associated with all of GlyGen's proteins and glycans with their corresponding GlyGen publication detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into three files."],"object_id":"https://biocomputeobject.org/GLY_000622/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5f3d8b4bb47ea75d568ac4a3d9b5a851"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.582000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000622/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.csv"}},{"uri":{"filename":"fruitfly_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_citations_biomarkers.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_biomarkers.csv"}},{"uri":{"filename":"human_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_matrixdb.csv"}},{"uri":{"filename":"human_protein_citations_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_germline.csv"}},{"uri":{"filename":"human_protein_citations_mutation_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_literature.csv"}},{"uri":{"filename":"human_protein_citations_mutation_somatic.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_somatic.csv"}},{"uri":{"filename":"human_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_reactome.csv"}},{"uri":{"filename":"human_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_refseq.csv"}},{"uri":{"filename":"human_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"human_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_matrixdb.csv"}},{"uri":{"filename":"mouse_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_refseq.csv"}},{"uri":{"filename":"mouse_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_matrixdb.csv"}},{"uri":{"filename":"rat_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_refseq.csv"}},{"uri":{"filename":"rat_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.csv"}},{"uri":{"filename":"fruitfly_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_citations_biomarkers.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_biomarkers.csv"}},{"uri":{"filename":"human_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_matrixdb.csv"}},{"uri":{"filename":"human_protein_citations_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_germline.csv"}},{"uri":{"filename":"human_protein_citations_mutation_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_literature.csv"}},{"uri":{"filename":"human_protein_citations_mutation_somatic.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_somatic.csv"}},{"uri":{"filename":"human_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_reactome.csv"}},{"uri":{"filename":"human_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_refseq.csv"}},{"uri":{"filename":"human_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"human_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_matrixdb.csv"}},{"uri":{"filename":"mouse_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_refseq.csv"}},{"uri":{"filename":"mouse_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_matrixdb.csv"}},{"uri":{"filename":"rat_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_refseq.csv"}},{"uri":{"filename":"rat_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.csv"}},{"uri":{"filename":"fruitfly_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_citations_biomarkers.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_biomarkers.csv"}},{"uri":{"filename":"human_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_matrixdb.csv"}},{"uri":{"filename":"human_protein_citations_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_germline.csv"}},{"uri":{"filename":"human_protein_citations_mutation_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_literature.csv"}},{"uri":{"filename":"human_protein_citations_mutation_somatic.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_somatic.csv"}},{"uri":{"filename":"human_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_reactome.csv"}},{"uri":{"filename":"human_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_refseq.csv"}},{"uri":{"filename":"human_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"human_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_matrixdb.csv"}},{"uri":{"filename":"mouse_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_refseq.csv"}},{"uri":{"filename":"mouse_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_citations_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_matrixdb.csv"}},{"uri":{"filename":"rat_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_refseq.csv"}},{"uri":{"filename":"rat_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_citations_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"uri":{"filename":"rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_citations_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_citations_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_one.csv","filename":"protein_ncbi_pubmed_linkouts_one.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_two.csv","filename":"protein_ncbi_pubmed_linkouts_two.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_three.csv","filename":"protein_ncbi_pubmed_linkouts_three.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_one.stat.csv","filename":"protein_ncbi_pubmed_linkouts_one.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_two.stat.csv","filename":"protein_ncbi_pubmed_linkouts_two.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_three.stat.csv","filename":"protein_ncbi_pubmed_linkouts_three.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}],"provenance_domain":{"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-28T16:49:07.908809","modified":"2022-03-29T12:20:53.052989","version":"v-2.1.1","name":"NCBI PubMed LinkOuts"},"description_domain":{"keywords":["NCBI PubMed","LinkOut","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/glycan_citations_glycomotif.csv","filename":"glycan_citations_glycomotif.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycation_uniprotkb.csv","filename":"human_proteoform_citations_glycation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_glyconnect.csv","filename":"human_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_harvard.csv","filename":"human_proteoform_citations_glycosylation_harvard.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_literature.csv","filename":"human_proteoform_citations_glycosylation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_literature_mining.csv","filename":"human_proteoform_citations_glycosylation_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"human_proteoform_citations_glycosylation_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_tyr_o_linked.csv","filename":"human_proteoform_citations_glycosylation_tyr_o_linked.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_unicarbkb.csv","filename":"human_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_uniprotkb.csv","filename":"human_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_iptmnet.csv","filename":"human_proteoform_citations_phosphorylation_iptmnet.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"human_proteoform_citations_phosphorylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_glyconnect.csv","filename":"mouse_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_literature_mining.csv","filename":"mouse_proteoform_citations_glycosylation_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_unicarbkb.csv","filename":"mouse_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_uniprotkb.csv","filename":"mouse_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_citations_phosphorylation_iptmnet.csv","filename":"mouse_proteoform_citations_phosphorylation_iptmnet.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/v-1.12.1reviewed/mouse_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"mouse_proteoform_citations_phosphorylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_citations_glycation_uniprotkb.csv","filename":"rat_proteoform_citations_glycation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_glyconnect.csv","filename":"rat_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_literature_mining.csv","filename":"rat_proteoform_citations_glycosylation_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_unicarbkb.csv","filename":"rat_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_uniprotkb.csv","filename":"rat_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_iptmnet.csv","filename":"rat_proteoform_citations_phosphorylation_iptmnet.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"rat_proteoform_citations_phosphorylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_literature.csv","filename":"sarscov1_proteoform_citations_glycosylation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_uniprotkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_glyconnect.csv","filename":"sarscov2_proteoform_citations_glycosylation_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_unicarbkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov2_proteoform_citations_glycosylation_uniprotkb.csv","filename":"sarscov2_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_literature.csv","filename":"hcv1a_proteoform_citations_glycosylation_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1a_proteoform_citations_glycosylation_uniprotkb.csv","filename":"hcv1a_proteoform_citations_glycosylation_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1b_proteoform_citations_glycosylation_uniprotkb.csv","filename":"hcv1b_proteoform_citations_glycosylation_uniprotkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_one.csv","filename":"protein_ncbi_pubmed_linkouts_one.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_two.csv","filename":"protein_ncbi_pubmed_linkouts_two.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/protein_ncbi_pubmed_linkouts_three.csv","filename":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-1.12.1/reviewed/protein_ncbi_pubmed_linkouts_three.csv"}],"prerequisite":[],"description":"The script loads the PubMed IDs from the input files associated with proteins and glycans in GlyGen and generates publication detail page URLs for corresponding proteins and glycans. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset that is split into three datasets"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["This dataset contains NCBI PubMed IDs associated with all of GlyGen's proteins and glycans with their corresponding GlyGen publication detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into three files."],"object_id":"https://biocomputeobject.org/GLY_000622/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f45f38cfd8ec422148a9426d37be33c0"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:12.668000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000623/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000623/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"84934b98eff37169e316b75991d6b764b4799ef061575d627bb2c61b187942bd","provenance_domain":{"name":"Human Glycogenes","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T10:11:35.122210","modified":"2026-03-26T15:04:51.908Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Kelley Moremen","affiliation":"University of Georgia","email":"moremen@uga.edu","contribution":["createdBy"]}]},"usability_domain":["This Human glycogenes dataset is retrieved a publication from UGA [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened human [taxonomy:9606] protein names mapped to NCBI gene and HGNC IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file."}],"keywords":["glycogenes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycogenes.csv","filename":"human_protein_glycogenes.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_glycogenes.stat.csv","filename":"human_protein_glycogenes.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycogenes","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1098,"last_update":"2026-03-26T15:04:51.908438Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000623/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"human_glycogenes.csv","uri":"https:/data.glygen.org/ln2downloads/glycogenes/2022_02_16/human_glycogenes.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycogenes.csv","filename":"human_protein_glycogenes.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycogenes.stat.csv","filename":"human_protein_glycogenes.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycogenes","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"orcid":"0000-0002-9920-565X","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T10:11:35.122210","modified":"2022-09-26T09:08:12.447031","version":"v-2.0.2","name":"Human Glycogenes"},"description_domain":{"keywords":["glycogenes"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2wwwdownloads/v-2.0.2/2022_02_16/human_glycogenes.csv","filename":"human_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_glycogenes.csv","filename":"human_protein_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/logs/human_protein_glycogenes.log","filename":"human_protein_glycogenes.log"}],"prerequisite":[],"description":"The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This Human glycogenes dataset is retrieved a publication from UGA [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened human [taxonomy:9606] protein names mapped to NCBI gene and HGNC IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy."],"object_id":"https://biocomputeobject.org/GLY_000623/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cbdc110b2ba31f761a517ab9e443469980ad3b5f8873e8381f3760133fe55aa3"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.551000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000623/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv"}},{"uri":{"filename":"human_glycogenes.csv","uri":"/data/shared/glyds/downloads/glycogenes/2022_02_16/human_glycogenes.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycogenes.csv","filename":"human_protein_glycogenes.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_glycogenes.stat.csv","filename":"human_protein_glycogenes.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycogenes","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T10:11:35.122210","modified":"2022-09-26T09:08:12.447031","version":"v-2.1.1","name":"Human Glycogenes"},"description_domain":{"keywords":["glycogenes"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2wwwdownloads/v-2.1.1/2022_02_16/human_glycogenes.csv","filename":"human_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_protein_glycogenes.csv","filename":"human_protein_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/logs/human_protein_glycogenes.log","filename":"human_protein_glycogenes.log"}],"prerequisite":[],"description":"The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This Human glycogenes dataset is retrieved a publication from UGA [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened human [taxonomy:9606] protein names mapped to NCBI gene and HGNC IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy."],"object_id":"https://biocomputeobject.org/GLY_000623/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3e90934ce6d32977268ab61e5d5d2e77"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:12.866000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000624/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000624/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"11c0060bdaa313c3f16dbfb4cb1f348bb0fef6fbfa3bb85972e3bacf246ec3c8","provenance_domain":{"name":"Mouse Glycogenes","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T10:34:01.428342","modified":"2026-03-26T14:59:59.216Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Kelley Moremen","affiliation":"University of Georgia","email":"moremen@uga.edu","contribution":["createdBy"]}]},"usability_domain":["This mouse glycogenes dataset is retrieved from stem cell analysis which was done with qRT-PCR analysis [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened mouse[taxonomy:10090] protein names mapped to NCBI gene and MGI IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file."}],"keywords":["glycogenes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycogenes.csv","filename":"mouse_protein_glycogenes.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_glycogenes.stat.csv","filename":"mouse_protein_glycogenes.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycogenes","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":1143,"last_update":"2026-03-26T14:59:59.216060Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000624/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_geneid.csv"}},{"uri":{"filename":"mouse_glycogenes.csv","uri":"https:/data.glygen.org/ln2downloads/glycogenes/2022_02_16/mouse_glycogenes.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycogenes.csv","filename":"mouse_protein_glycogenes.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_glycogenes.stat.csv","filename":"mouse_protein_glycogenes.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycogenes","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"orcid":"0000-0002-9920-565X","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T10:34:01.428342","modified":"2022-09-26T09:08:12.595449","version":"v-2.0.2","name":"Mouse Glycogenes"},"description_domain":{"keywords":["glycogenes"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2wwwdownloads/v-2.0.2/2022_02_16/mouse_glycogenes.csv","filename":"mouse_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_protein_glycogenes.csv","filename":"mouse_protein_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/logs/mouse_protein_glycogenes.log","filename":"mouse_protein_glycogenes.log"}],"prerequisite":[],"description":"The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This mouse glycogenes dataset is retrieved from stem cell analysis which was done with qRT-PCR analysis [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened mouse[taxonomy:10090] protein names mapped to NCBI gene and MGI IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy. "],"object_id":"https://biocomputeobject.org/GLY_000624/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"db96f36902848112609df3d0c3fde3b0ecff318af8879ab1eebdbac879da3279"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.418000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000624/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_xref_geneid.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv"}},{"uri":{"filename":"mouse_glycogenes.csv","uri":"/data/shared/glyds/downloads/glycogenes/2022_02_16/mouse_glycogenes.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycogenes.csv","filename":"mouse_protein_glycogenes.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_glycogenes.stat.csv","filename":"mouse_protein_glycogenes.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycogenes","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T10:34:01.428342","modified":"2022-09-26T09:08:12.595449","version":"v-2.1.1","name":"Mouse Glycogenes"},"description_domain":{"keywords":["glycogenes"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2wwwdownloads/v-2.1.1/2022_02_16/mouse_glycogenes.csv","filename":"mouse_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_protein_glycogenes.csv","filename":"mouse_protein_glycogenes.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/logs/mouse_protein_glycogenes.log","filename":"mouse_protein_glycogenes.log"}],"prerequisite":[],"description":"The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This mouse glycogenes dataset is retrieved from stem cell analysis which was done with qRT-PCR analysis [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened mouse[taxonomy:10090] protein names mapped to NCBI gene and MGI IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy. "],"object_id":"https://biocomputeobject.org/GLY_000624/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"317dbeb2ad3c0992fcc3859b7925ca54"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:13.061000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000625/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000625/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3795edc13d1ba9f9b64689cb35fbf3a0681425a0804796104725628ef5468560","provenance_domain":{"name":"Human Protein Biomarkers (Biomarker Database)","version":"v-0.0.0","created":"2022-03-29T11:06:26.279356","modified":"2024-05-17T11:24:07.032Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Daniel Lyman","contribution":["curatedBy"],"affiliation":"The George Washington University","email":"danlyman@email.gwu.edu","orcid":""},{"name":"Biomarker DB","contribution":["createdBy","importedFrom"],"affiliation":"","email":"","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This is a Human Protein Biomarkers dataset. It contains human [taxonomy:9606] protein biomarker information, including cross-mapped UniProtKB or Protein Ontology accessions, assessed biomarker entity, biomarker status, biomarker type, specimen type, LOINC code, disease name, and source evidence from the cancer biomarker portal (https://data.oncomx.org/cancerbiomarkers). This dataset can be used to obtain biomarker information for 19 cancer types and COVID-19. If you use this dataset, please provide proper attribution to OncoMX and GlyGen. Cite: PMID:32142370, PMID:34015823, and PMID:31616925. The dataset was earlier called as human_protein_cancer_biomarkers.csv"],"description_domain":{"keywords":["biomarker","cancer"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script maps the UniProtKB accession from the source file to UniProtKB canonical accession. The script extracts the other fields as is from the source input file."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_biomarkers.csv","filename":"human_protein_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_biomarkers.stat.csv","filename":"human_protein_biomarkers.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Biomarker (BiomarkerDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":669,"last_update":"2024-05-17T11:24:07.032292Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000625/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"doid2uberonid_mapping_v5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/doid2uberonid_mapping_v5.csv"}},{"uri":{"filename":"glygen_human_protein_biomarkers_cancer.csv","uri":"https:/data.glygen.org/ln2downloads/biomarkerdb/2022_03_14/glygen_human_protein_biomarkers_cancer.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_biomarkers_cancer.csv","filename":"human_protein_biomarkers_cancer.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_biomarkers_cancer.stat.csv","filename":"human_protein_biomarkers_cancer.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Biomarker (BiomarkerDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"orcid":"0000-0002-9920-565X","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Amanda Bell","email":"amandab2140@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Millicent Quartey","email":"mquartey@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T11:06:26.279356","modified":"2022-09-26T09:08:12.572556","version":"v-2.0.2","name":"Human Protein Cancer Biomarkers (Biomarker Portal)"},"description_domain":{"keywords":["biomarker","cancer"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2wwwdownloads/v-2.0.2/2022_03_14/glygen_human_protein_biomarkers_cancer.csv","filename":"glygen_human_protein_biomarkers_cancer.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_protein_biomarkers_cancer.csv","filename":"human_protein_biomarkers_cancer.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accession from the source file to UniProtKB canonical accession. The script extracts the other fields as is from the source input file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This is a Human Protein Cancer Biomarkers dataset. It contains human [taxonomy:9606] cancer biomarker information including biomarker main x-ref mapped to UniProtKB, assessed biomarker entity, BEST biomarker type, literature evidence, disease name. and LOINC code from the cancer biomarker portal (https://data.oncomx.org/cancerbiomarkers). If you use this dataset, please provide proper attribution to OncoMX and GlyGen. Cite:PMID:32142370, PMID:34015823, and PMID:31616925. This dataset can be used for obtaining cancer biomarker information for 19 cancer types."],"object_id":"https://biocomputeobject.org/GLY_000625/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"88a242d42a9206611ed79a216860c61e45cb073f22db4954760cc5ac18ecadca"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.539000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000625/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000625/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"53b80d390cdc9b8b6f2c1cae0718902e","provenance_domain":{"name":"Human Protein Biomarkers (Biomarker Database)","version":"v-2.1.1","created":"2022-03-29T11:06:26.279356","modified":"2023-03-14T16:22:16.567Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Daniel Lyman","contribution":["curatedBy"],"affiliation":"The George Washington University","email":"danlyman@email.gwu.edu","orcid":""},{"name":"Biomarker DB","contribution":["createdBy","importedFrom"],"affiliation":"","email":"","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This is a Human Protein Biomarkers dataset. It contains human [taxonomy:9606] protein biomarker information, including cross-mapped UniProtKB or Protein Ontology accessions, assessed biomarker entity, biomarker status, biomarker type, specimen type, LOINC code, disease name, and source evidence from the cancer biomarker portal (https://data.oncomx.org/cancerbiomarkers). This dataset can be used to obtain biomarker information for 19 cancer types and COVID-19. If you use this dataset, please provide proper attribution to OncoMX and GlyGen. Cite: PMID:32142370, PMID:34015823, and PMID:31616925. The dataset was earlier called as human_protein_cancer_biomarkers.csv"],"description_domain":{"keywords":["biomarker","cancer"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""},{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accession from the source file to UniProtKB canonical accession. The script extracts the other fields as is from the source input file."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"doid2uberonid_mapping_v5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/doid2uberonid_mapping_v5.csv"}},{"uri":{"filename":"allbiomarkers-all.csv","uri":"/data/shared/glyds/downloads/biomarkerdb/2023_04_13/allbiomarkers-all.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_biomarkers.csv","filename":"human_protein_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_biomarkers.stat.csv","filename":"human_protein_biomarkers.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Biomarker (BiomarkerDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:04.142000Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000627/DRAFT","contents":{"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_genecards_xref_mapping.tsv","filename":"protein_glygen_genecards_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_genecards_xref_mapping.stat.csv","filename":"protein_glygen_genecards_xref_mapping.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-GeneCards Crossreferences","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T12:16:21.978852","modified":"2024-05-17T11:24:07.070Z","version":"v-0.0.0","name":"GlyGen-GeneCards Crossreferences Mapping"},"description_domain":{"keywords":["GeneCards","GlyGen","crossreferences"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"object_id":"https://biocomputeobject.org/GLY_000627/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f9396b5a0b40cbaa2053faa43a6c0f8fd30e92545a976010db41130170375244","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:07.070748Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000627/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_genecards_xref_mapping.tsv","filename":"protein_glygen_genecards_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_genecards_xref_mapping.stat.csv","filename":"protein_glygen_genecards_xref_mapping.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-GeneCards Crossreferences","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T12:16:21.978852","modified":"2022-09-26T09:08:12.682068","version":"v-2.0.2","name":"GlyGen-GeneCards Crossreferences Mapping"},"description_domain":{"keywords":["GeneCards","GlyGen","crossreferences"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3//v-2.0.2/reviewed/protein_glygen_genecards_xref_mapping.tsv","filename":"protein_glygen_genecards_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"object_id":"https://biocomputeobject.org/GLY_000627/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b5679a8837ff8ef75fadf669d384bfd4135e911c9da1eef8bc3a698c8c7b3bbe","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:53.467000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000627/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_genecards_xref_mapping.tsv","filename":"protein_glygen_genecards_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_genecards_xref_mapping.stat.csv","filename":"protein_glygen_genecards_xref_mapping.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-GeneCards Crossreferences","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T12:16:21.978852","modified":"2023-09-13T15:47:00","version":"v-2.1.1","name":"GlyGen-GeneCards Crossreferences Mapping"},"description_domain":{"keywords":["GeneCards","GlyGen","crossreferences"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv","filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-1.12.3//v-2.1.1/reviewed/protein_glygen_genecards_xref_mapping.tsv","filename":"protein_glygen_genecards_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"object_id":"https://biocomputeobject.org/GLY_000627/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d429dc6bd7dc34a5bf27d2c1ca645199977db846","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-09-13T15:47:05.242000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000628/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000628/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"97aa0e00d56d76b2fd2db52fb263185d5d512634a080d7360f234bc61fbaf3e6","provenance_domain":{"name":"SARS-CoV1 Glycosylation Sites (UniCarbKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-31T15:05:49.377202","modified":"2024-12-05T19:05:06.063Z","contributors":[{"name":"Karina Martinez","affiliation":"The George Washington University","email":"karinamartinez@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Griffith University","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This is a SARS-CoV-1 Glycosylation Sites (UniCarbKB) dataset. It contains a list of Severe acute respiratory syndrome-related coronavirus (SARS-CoV-1) [taxonomy:694009] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB. The listed proteins (UniProtKB accession) are part of the GlyGen UniProtKB SARS CoV1 Proteome Masterlist (https://data.glygen.org/GLY_000467). If you use this dataset, please provide proper attribution to UniCarbKB, EMBL-EBI-UniProtKB, and GlyGen. Cite: PMID:24234447, PMID:33237286, and PMID:31616925. This dataset can be used for obtaining a list of glycosylation sites for canonical glycoproteins from the UnicarbKB database."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[]}],"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":845,"last_update":"2024-12-05T19:05:06.063849Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000628/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Griffith University","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-31T15:05:49.377202","modified":"2022-09-26T09:08:12.642745","version":"v-2.0.2","name":"SARS-CoV1 Glycosylation Sites (UniCarbKB)"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2downloads/v-2.0.2/01_11_2022/known_33064451_glygen.csv","filename":"known_33064451_glygen.csv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"http://data.glygen.org/ln2downloads/glytoucan/v-2.0.2/export/classification.tsv","filename":"classification.tsv"},{"uri":"http://data.glygen.org/ln2downloads/glytoucan/v-2.0.2/export/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/misc/aadict.csv","filename":"aadict.csv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This is a SARS-CoV1 Glycosylation Sites (UniCarbKB) dataset. It contains a list of SARS coronavirus (SARS-CoV-1) [taxonomy:694009] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB. The listed proteins (UniProtKB accession) are part of the GlyGen UniProtKB SARS CoV1 Proteome Masterlist (https://data.glygen.org/GLY_000467). If you use this dataset, please provide proper attribution to UniCarbKB, EMBL-EBI-UniProtKB, and GlyGen. Cite: PMID:24234447, PMID:33237286, and PMID:31616925. This dataset can be used for obtaining a list of glycosylation sites for canonical glycoproteins from the UnicarbKB database."],"object_id":"https://biocomputeobject.org/GLY_000628/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"faba1fb5c4a5b6b4eb8377f85956416b3d5c576306c24b97c2c620db70b601f2","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.514000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000628/v-2.1.1","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"fuzzy_legacy_cph_start_end_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv"}},{"uri":{"filename":"fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv"}},{"uri":{"filename":"fuzzy_legacy_qin_oglanac.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv"}},{"uri":{"filename":"fuzzy_simplecell_all_glygen_qc.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv"}},{"uri":{"filename":"known_33064451_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv"}},{"uri":{"filename":"known_33167210_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv"}},{"uri":{"filename":"known_33806155_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv"}},{"uri":{"filename":"known_34004174_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv"}},{"uri":{"filename":"known_34106099_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv"}},{"uri":{"filename":"known_legacy_cph_single_positions.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv"}},{"uri":{"filename":"known_legacy_dbogap_dbogap2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv"}},{"uri":{"filename":"known_legacy_human_mouse_rat_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv"}},{"uri":{"filename":"known_legacy_larsson_xyl.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv"}},{"uri":{"filename":"known_legacy_reis_gastric_ags.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv"}},{"uri":{"filename":"known_legacy_sarscov2_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"mixed_34089345_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv"}},{"uri":{"filename":"unknown_20131323_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv"}},{"uri":{"filename":"unknown_33993882_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv"}},{"uri":{"filename":"unknown_34083726_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv"}},{"uri":{"filename":"unknown_34191522_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv"}},{"uri":{"filename":"unknown_34327564_glygen.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv"}},{"uri":{"filename":"unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Griffith University","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-31T15:05:49.377202","modified":"2022-09-26T09:08:12.642745","version":"v-2.1.1","name":"SARS-CoV1 Glycosylation Sites (UniCarbKB)"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"uri":"http://data.glygen.org/ln2downloads/v-2.1.1/01_11_2022/known_33064451_glygen.csv","filename":"known_33064451_glygen.csv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"uri":"http://data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/classification.tsv","filename":"classification.tsv"},{"uri":"http://data.glygen.org/ln2downloads/glytoucan/v-2.1.1/export/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/misc/aadict.csv","filename":"aadict.csv"},{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This is a SARS-CoV1 Glycosylation Sites (UniCarbKB) dataset. It contains a list of SARS coronavirus (SARS-CoV-1) [taxonomy:694009] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB. The listed proteins (UniProtKB accession) are part of the GlyGen UniProtKB SARS CoV1 Proteome Masterlist (https://data.glygen.org/GLY_000467). If you use this dataset, please provide proper attribution to UniCarbKB, EMBL-EBI-UniProtKB, and GlyGen. Cite: PMID:24234447, PMID:33237286, and PMID:31616925. This dataset can be used for obtaining a list of glycosylation sites for canonical glycoproteins from the UnicarbKB database."],"object_id":"https://biocomputeobject.org/GLY_000628/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4f4633440a6186b9c746b080863e29c8","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:13.543000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000629/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000629/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"807879afa69997a3f5d958273fd23690872d2f342eff4fc17ac793d6bbbb0e32","provenance_domain":{"name":"SARS-CoV1 Proteoform Citations (UniCarbKB)","version":"v-0.0.0","created":"2022-03-31T16:48:58.298751","modified":"2024-12-05T19:18:24.496Z","contributors":[{"name":"Karina Martinez","affiliation":"The George Washington University","email":"karinamartinez@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Griffith University","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Citation details (such as title, journal_name, publication_date, authors) corresponding to the Digital Object Identifiers (DOI)/PMID present in the UniCarbKB SARS-CoV1 Glycosylation Sites dataset (https://data.glygen.org/GLY_000628). If you use this dataset, please provide proper attribution to UniCarbKB, EMBL-EBI-UniProtKB, and GlyGen. Cite: PMID:26940363, PMID:33237286, and PMID:31616925. This dataset can be used for obtaining publication information for UniCarbKB glycosylation data."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["Proteins","DOI (Digital Object Identifier)"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py ","filename":"make-proteoform-dataset.py"}}],"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":593,"last_update":"2024-12-05T19:18:24.496346Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000629/v-2.0.2","contents":{"io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/doi_citations.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_unicarbkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_unicarbkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_unicarbkb.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_unicarbkb.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Citation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Griffith University","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"}],"license":"","created":"2022-03-31T16:48:58.298751","modified":"2022-09-26T09:08:12.547380","version":"v-2.0.2","name":"SARS-CoV1 Proteoform Citations (UniCarbKB)"},"description_domain":{"keywords":["Proteins","DOI (Digital Object Identifier)"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.0.2/reviewed/sarscov1_proteoform_citations_glycosylation_unicarbkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_unicarbkb.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py ","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Citation details (such as title, journal_name, publication_date, authors) corresponding to the Digital Object Identifiers (DOI)/PMID present in the UniCarbKB SARS-CoV1 Glycosylation Sites dataset (https://data.glygen.org/GLY_000628). If you use this dataset, please provide proper attribution to UniCarbKB, EMBL-EBI-UniProtKB, and GlyGen. Cite: PMID:26940363, PMID:33237286, and PMID:31616925. This dataset can be used for obtaining publication information for UniCarbKB glycosylation data."],"object_id":"https://biocomputeobject.org/GLY_000629/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"78a4fba95d89de4120da444ab331f95c36e41a7a2ea6b72b5dd85732323dd995","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:09.251000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000629/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000629/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bd86fd863a7a03f4aa1b4616b12d32c6","provenance_domain":{"name":"SARS-CoV1 Proteoform Citations (UniCarbKB)","version":"v-2.1.1","created":"2022-03-31T16:48:58.298751","modified":"2023-03-14T16:18:14.857Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"affiliation":"Griffith University","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":""},"usability_domain":["Citation details (such as title, journal_name, publication_date, authors) corresponding to the Digital Object Identifiers (DOI)/PMID present in the UniCarbKB SARS-CoV1 Glycosylation Sites dataset (https://data.glygen.org/GLY_000628). If you use this dataset, please provide proper attribution to UniCarbKB, EMBL-EBI-UniProtKB, and GlyGen. Cite: PMID:26940363, PMID:33237286, and PMID:31616925. This dataset can be used for obtaining publication information for UniCarbKB glycosylation data."],"description_domain":{"keywords":["Proteins","DOI (Digital Object Identifier)"],"platform":[],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":""}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py ","filename":"make-proteoform-dataset.py"}}],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/doi_citations.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov1_proteoform_citations_glycosylation_sites_unicarbkb.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Citation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:04.716000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000630/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Glycosylation Sites (GlyConnect) ","version":"v-0.0.0","created":"2022-08-16T12:24:13.810189","modified":"2024-05-17T11:24:07.187Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosylation Sites (GlyConnect) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported glycans in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Drosophila melanogaster). If you use this dataset please provide proper attribution to GlyConnect and GlyGen. Please note that this dataset does not contain protein or sites information just the glycans"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the latest UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (fruitfly_proteoform_glycosylation_sites_glyconnect.1.log) In this dataset the script only extracts the glycan information. CURRENTLY - THE ABOVE QC STEP IS NOT DONE AS THE DATA DOES NOT HAVE PROTEIN AND SITES.","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000630/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ba4ad83540fb3c15f4c5a0c820e0c0a7ac81d9f42ad59f071dfc2e8a3ae95710"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":612,"last_update":"2024-05-17T11:24:07.187304Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000630/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Glycosylation Sites (GlyConnect) ","version":"v-2.0.2","created":"2022-08-16T12:24:13.810189","modified":"2022-09-26T09:08:12.690956","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosylation Sites (GlyConnect) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported glycans in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Drosophila melanogaster). If you use this dataset please provide proper attribution to GlyConnect and GlyGen. Please note that this dataset does not contain protein or sites information just the glycans"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the latest UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (fruitfly_proteoform_glycosylation_sites_glyconnect.1.log) In this dataset the script only extracts the glycan information. CURRENTLY - THE ABOVE QC STEP IS NOT DONE AS THE DATA DOES NOT HAVE PROTEIN AND SITES.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glyconnect_fruitfly.json","filename":"glyconnect_fruitfly.json"},{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"output_list":[{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.0.2/logs/fruitfly_proteoform_glycosylation_sites_glyconnect.1.log","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.1.log"},{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"glyconnect_fruitfly.json","uri":"https:/data.glygen.org/ln2downloads/glyconnect/2022_03_14/glyconnect_fruitfly.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000630/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"acf6c3f56dce3dd4a373f606e053789982ae6e91310eb248ec7955f3b5a2f10c"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.198000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000630/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Glycosylation Sites (GlyConnect) ","version":"v-2.1.1","created":"2022-08-16T12:24:13.810189","modified":"2022-09-26T09:08:12.690956","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosylation Sites (GlyConnect) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported glycans in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Drosophila melanogaster). If you use this dataset please provide proper attribution to GlyConnect and GlyGen. Please note that this dataset does not contain protein or sites information just the glycans"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the latest UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (fruitfly_proteoform_glycosylation_sites_glyconnect.1.log) In this dataset the script only extracts the glycan information. CURRENTLY - THE ABOVE QC STEP IS NOT DONE AS THE DATA DOES NOT HAVE PROTEIN AND SITES.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glyconnect_fruitfly.json","filename":"glyconnect_fruitfly.json"},{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"output_list":[{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.1.1/logs/fruitfly_proteoform_glycosylation_sites_glyconnect.1.log","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.1.log"},{"uri":"https:/data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"glycosylations?taxonomy=Drosophila melanogaster","uri":"/data/shared/glyds/downloads/glyconnect/2023_05_18/glycosylations?taxonomy=Drosophila melanogaster"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000630/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"40ca70c3415285c6dd3e7e15c20efedd"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:13.858000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000631/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000631/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"223a463cded2db7654c074d73e39a02fb1721e4e77aa57f128907ec19637061e","provenance_domain":{"name":"Mouse O-GlcNAc Glycosylation Sites (MCW)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:48:29.540934","modified":"2024-12-10T17:36:36.458Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse O-GlcNAc Glycosylation Sites (MCW) contains Mus musculus [taxid:10090] O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s mouse protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to mouse species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding mouse UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":2965,"last_update":"2024-12-10T17:36:36.458934Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000631/v-2.0.2","contents":{"provenance_domain":{"name":"Mouse O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.0.2","created":"2022-08-16T20:48:29.540934","modified":"2022-09-26T09:08:12.684109","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Sites (MCW) contains mouse (taxid:10090) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s mouse protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to mouse species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding mouse UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/mouse_o-glcnacome_mcw.csv","filename":"mouse_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.log"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_info_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_recnames.csv"}},{"uri":{"filename":"mouse_o-glcnacome_mcw.csv","uri":"https:/data.glygen.org/ln2downloads/mcw_oglcnac/2022_07_29/mouse_o-glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000631/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8567a451e3ef6d0f3cc99a46d19c9ab4d73ac63c92bc0228b2822f49b24398df","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:48.898000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000631/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000631/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8bb3b016fc22abce2c30be4db9428b06","provenance_domain":{"name":"Mouse O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.1.1","created":"2022-08-16T20:48:29.540934","modified":"2023-03-14T17:06:01.680Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Sites (MCW) contains mouse (taxid:10090) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s mouse protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to mouse species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding mouse UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"keywords":["O-GlcNAc"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/mouse_o-glcnacome_mcw.csv","filename":"mouse_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.log"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"mouse_o_glcnacome_mcw.csv","uri":"/data/shared/glyds/downloads/mcw_oglcnac/2023_04/mouse_o_glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:14.036000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000632/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000632/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"488ffdea7136831d7b4844215e35666ed98281a597e6f72eb60dbb65930b4a2c","provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Sites (MCW)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:53:24.527843","modified":"2024-12-05T18:47:30.152Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat O-GlcNAc Glycosylation Sites (MCW) contains Rattus norvegicus (taxid:10116) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s rat protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to rat species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding rat UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus Norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":2960,"last_update":"2024-12-05T18:47:30.152432Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000632/v-2.0.2","contents":{"provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.0.2","created":"2022-08-16T20:53:24.527843","modified":"2022-09-26T09:08:12.597194","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat O-GlcNAc Glycosylation Sites (MCW) contains rat (taxid:10116) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s rat protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to rat species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding rat UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus Norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/rat_o-glcnacome_mcw.csv","filename":"rat_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/rat_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.log"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_info_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_recnames.csv"}},{"uri":{"filename":"rat_o-glcnacome_mcw.csv","uri":"https:/data.glygen.org/ln2downloads/mcw_oglcnac/2022_07_29/rat_o-glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000632/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"496c8f752f26bb7a255bb5b56f968e2be47c5a74015feead2467af2b47637c04","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.840000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000632/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000632/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"29e3e2211a2513bce9a6c7b1de613de4","provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.1.1","created":"2022-08-16T20:53:24.527843","modified":"2023-03-14T17:07:58.191Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat O-GlcNAc Glycosylation Sites (MCW) contains rat (taxid:10116) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s rat protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to rat species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding rat UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"keywords":["O-GlcNAc"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/rat_o-glcnacome_mcw.csv","filename":"rat_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/rat_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.log"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_info_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"rat_o_glcnacome_mcw.csv","uri":"/data/shared/glyds/downloads/mcw_oglcnac/2023_04/rat_o_glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus Norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:14.239000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000633/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000633/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f6db246c8b73fdc8b005b8cfb400a9ca419980dc320ff16b4ce14d6b6cee0105","provenance_domain":{"name":"Fruitfly O-GlcNAc Glycosylation Sites (MCW)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:56:25.251283","modified":"2024-12-03T18:18:50.047Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Sites (MCW) contains Drosophila melanogaster (taxid:7227) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Fruitfly O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s fruitfly protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to fruitfly species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding fruitfly UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":2994,"last_update":"2024-12-03T18:18:50.047618Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000633/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.0.2","created":"2022-08-16T20:56:25.251283","modified":"2022-09-26T09:08:12.568728","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Sites (MCW) contains fruitfly (taxid:7227) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Fruitfly O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s fruitfly protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to fruitfly species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding fruitfly UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/fruitfly_o-glcnacome_mcw.csv","filename":"fruitfly_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_allsequences.fasta","filename":"fruitfly_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/logs/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.log"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_info_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_recnames.csv"}},{"uri":{"filename":"fruitfly_o-glcnacome_mcw.csv","uri":"https:/data.glygen.org/ln2downloads/mcw_oglcnac/2022_07_29/fruitfly_o-glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000633/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a2cf4e4f9fb8b2c855e5b233c91ae8c991e8345bd609700baa275892de58d966","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.954000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000633/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000633/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"507ef134e7bd7b8093e2f5481881409f3d20d266","provenance_domain":{"name":"Fruitfly O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.1.1","created":"2022-08-16T20:56:25.251283","modified":"2023-09-13T19:10:29","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Sites (MCW) contains fruitfly (taxid:7227) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Fruitfly O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s fruitfly protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to fruitfly species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding fruitfly UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"keywords":["O-GlcNAc"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/fruitfly_o-glcnacome_mcw.csv","filename":"fruitfly_o-glcnacome_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_allsequences.fasta","filename":"fruitfly_protein_allsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/logs/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.log"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"fruitfly_o_glcnacome_mcw.csv","uri":"/data/shared/glyds/downloads/mcw_oglcnac/2023_04/fruitfly_o_glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-09-13T19:10:31.693000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000634/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Isoform sequences (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T12:21:27.326808","modified":"2024-05-17T11:24:07.336Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Isoform sequences (UniProtKB) dataset contains fruitfly [taxid:7227] protein fasta sequences for the fruitfly isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_allsequences.fasta","filename":"fruitfly_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_allsequences.stat.csv","filename":"fruitfly_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000634/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5c445e6bd962582858ed5252f374bfa78a7bd8a29fc57a78ab5dbd9477d185ef"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":269,"last_update":"2024-05-17T11:24:07.336805Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000634/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Isoform sequences (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T12:21:27.326808","modified":"2022-09-26T09:08:12.539404","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Isoform sequences (UniProtKB) dataset contains fruitfly [taxid:7227] protein fasta sequences for the fruitfly isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_allsequences.fasta","filename":"fruitfly_protein_allsequences.fasta"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_allsequences.fasta","filename":"fruitfly_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_allsequences.stat.csv","filename":"fruitfly_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000634/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9aca4ef9e033b4a5684e0531e854d9d9c3ceb476b470ab81d6378da0b9f3fa4e"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.814000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000634/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Isoform sequences (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T12:21:27.326808","modified":"2022-09-26T09:08:12.539404","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Isoform sequences (UniProtKB) dataset contains fruitfly [taxid:7227] protein fasta sequences for the fruitfly isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_allsequences.fasta","filename":"fruitfly_protein_allsequences.fasta"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_allsequences.fasta","filename":"fruitfly_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_allsequences.stat.csv","filename":"fruitfly_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000634/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3062b7cc05a6ec246968d85737282ba8"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:14.677000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000635/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Alternative Name (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T13:19:31.385999","modified":"2024-05-17T11:24:07.374Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_altnames.csv","filename":"fruitfly_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_altnames.stat.csv","filename":"fruitfly_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000635/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"32fac4d3221d0ee31dfec0c2a4016c9579ef8a0b1788488c70d5cea223e0d424"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":221,"last_update":"2024-05-17T11:24:07.374269Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000635/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Alternative Name (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T13:19:31.385999","modified":"2022-09-26T09:08:12.445889","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_altnames.csv","filename":"fruitfly_protein_altnames.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_altnames.csv","filename":"fruitfly_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_altnames.stat.csv","filename":"fruitfly_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000635/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8839ab6e8b03cb56c1a34c97c5a34d32efaf3355307336468890dea862d2eedd"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.321000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000635/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Alternative Name (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T13:19:31.385999","modified":"2022-09-26T09:08:12.445889","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_altnames.csv","filename":"fruitfly_protein_altnames.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_altnames.csv","filename":"fruitfly_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_altnames.stat.csv","filename":"fruitfly_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000635/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"93e75603de27609ea9ee812a5b1d9db8"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:14.886000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000636/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Canonical sequences (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T14:04:28.411067","modified":"2024-05-17T11:24:07.411Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Canonical (UniProtKB) Sequences dataset contains fruitfly [taxid:7227] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all fruitfly canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_canonicalsequences.fasta","filename":"fruitfly_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_canonicalsequences.stat.csv","filename":"fruitfly_protein_canonicalsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000636/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2d9c2e929d8493b43fb8e57f08e1d105c938b19c6883da29117bd78a253bec7d"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":245,"last_update":"2024-05-17T11:24:07.411698Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000636/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Canonical sequences (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T14:04:28.411067","modified":"2022-09-26T09:08:12.757432","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Canonical (UniProtKB) Sequences dataset contains fruitfly [taxid:7227] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all fruitfly canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/v-2.0.2/reviewed/fruitfly_protein_canonicalsequences.fasta","filename":"fruitfly_protein_canonicalsequences.fasta"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_canonicalsequences.fasta","filename":"fruitfly_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_canonicalsequences.stat.csv","filename":"fruitfly_protein_canonicalsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000636/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0ea77d132fb9e44312e66fd8e8fddba453302345a0e6d8b3d0943d00e7faaa95"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.303000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000636/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Canonical sequences (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T14:04:28.411067","modified":"2022-09-26T09:08:12.757432","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Canonical (UniProtKB) Sequences dataset contains fruitfly [taxid:7227] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all fruitfly canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/v-2.1.1/reviewed/fruitfly_protein_canonicalsequences.fasta","filename":"fruitfly_protein_canonicalsequences.fasta"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_canonicalsequences.fasta","filename":"fruitfly_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_canonicalsequences.stat.csv","filename":"fruitfly_protein_canonicalsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000636/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dfc837293b8a9c66f82b7d19d9801cc7"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:15.082000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000637/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Citations (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T14:17:09.307325","modified":"2024-05-17T11:24:07.448Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Citations dataset contains publication information for Drosophila melanogaster [taxid:7227] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_citations_uniprotkb.csv","filename":"fruitfly_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_citations_uniprotkb.stat.csv","filename":"fruitfly_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{},"object_id":"https://biocomputeobject.org/GLY_000637/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e31c79a3739c7b082c544bd0cc9b1335a0d0e4ef4f428457d0d0167698d7930a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":430,"last_update":"2024-05-17T11:24:07.448887Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000637/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Citations (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T14:17:09.307325","modified":"2022-09-26T09:08:12.727097","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Citations dataset contains publication information for fruitfly [taxid:7227] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/fruitfly_protein_blacklisted_pmids_uniprotkb.csv. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/fruitfly_protein_blacklisted_pmids_uniprotkb.csv","filename":"fruitfly_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_citations_uniprotkb.csv","filename":"fruitfly_protein_citations_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_citations_uniprotkb.csv","filename":"fruitfly_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_citations_uniprotkb.stat.csv","filename":"fruitfly_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000637/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c602995925caab09f524b5c2d8fab9feef2e28871ac49f0620b8ef94aa1798fa"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:05.064000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000637/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Citations (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T14:17:09.307325","modified":"2022-09-26T09:08:12.727097","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Citations dataset contains publication information for fruitfly [taxid:7227] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/fruitfly_protein_blacklisted_pmids_uniprotkb.csv. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/fruitfly_protein_blacklisted_pmids_uniprotkb.csv","filename":"fruitfly_protein_blacklisted_pmids_uniprotkb.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_uniprotkb.csv","filename":"fruitfly_protein_citations_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_uniprotkb.csv","filename":"fruitfly_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_uniprotkb.stat.csv","filename":"fruitfly_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000637/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f3ee4bccc4efb4b8b12215421e33a7c6"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:15.290000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000638/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Enzyme Annotation (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T14:44:26.008676","modified":"2024-06-03T20:44:14.557Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Enzyme Annotation (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000638/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ee78b1960add0238139968c16cb4d1b140330a7152ccb6d7b3b6493d4c2ec8f4","error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-06-03T20:44:14.557904Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000638/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Enzyme Annotation (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T14:44:26.008676","modified":"2022-09-26T09:08:12.523790","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Enzyme Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions.  The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000638/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5cc46d1524fef2b3ca558d97b4b6df3827d6865c4a0497dc9ccbbb5cdb622767","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.996000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000638/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Enzyme Annotation (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T14:44:26.008676","modified":"2022-09-26T09:08:12.523790","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Enzyme Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions.  The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000638/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"41175de22ae134a184868b61be1eb744","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:15.489000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000639/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Function (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T14:58:43.098400","modified":"2024-05-17T11:24:07.523Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Function (UniProtKB) dataset contains biological function annotation for fruitfly [taxid:7227] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_function_uniprotkb.csv","filename":"fruitfly_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_function_uniprotkb.stat.csv","filename":"fruitfly_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000639/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2aa373e56f38e34a6874878e877edfbe06fd7462addb0dfd19b6135b5404118a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":256,"last_update":"2024-05-17T11:24:07.523250Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000639/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Function (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T14:58:43.098400","modified":"2022-09-26T09:08:12.461522","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Function (UniProtKB) dataset contains biological function annotation for fruitfly [taxid:7227] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_function_uniprotkb.csv","filename":"fruitfly_protein_function_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_function_uniprotkb.csv","filename":"fruitfly_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_function_uniprotkb.stat.csv","filename":"fruitfly_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000639/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0d5572d6ca592a6cbae36645a2b5785dba7a467f526d61007d8e4a961f251486"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:56.616000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000639/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Function (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T14:58:43.098400","modified":"2022-09-26T09:08:12.461522","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Function (UniProtKB) dataset contains biological function annotation for fruitfly [taxid:7227] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_function_uniprotkb.csv","filename":"fruitfly_protein_function_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_function_uniprotkb.csv","filename":"fruitfly_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_function_uniprotkb.stat.csv","filename":"fruitfly_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000639/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"66a9455a0b52253303f6f2fd1c903d1d"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:15.700000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000640/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Gene Locus (Ensembl)","version":"v-0.0.0","created":"2020-04-10T11:29:22.824792","modified":"2024-05-17T11:24:07.560Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Locus (Ensembl) contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_genelocus.csv","filename":"fruitfly_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_genelocus.stat.csv","filename":"fruitfly_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000640/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d95eeb7c7b6ba15de2865a040c7cf24940c84451a8d904cee510b4dc7e14a396"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":325,"last_update":"2024-05-17T11:24:07.560905Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000640/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Gene Locus (Ensembl)","version":"v-2.0.2","created":"2020-04-10T11:29:22.824792","modified":"2022-09-26T09:08:12.732452","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Locus (Ensembl) contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_genelocus.csv","filename":"fruitfly_protein_genelocus.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"Drosophila_melanogaster.BDGP6.32.104.gtf","uri":"https:/data.glygen.org/ln2downloads/ucsc/gtf/Drosophila_melanogaster.BDGP6.32.104.gtf"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_genelocus.csv","filename":"fruitfly_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_genelocus.stat.csv","filename":"fruitfly_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000640/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dc9ba57eb818e56b7043ef762289622ec5b3dc7060c76bd03cf8b82081bc1e7a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:23.703000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000640/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Gene Locus (Ensembl)","version":"v-2.1.1","created":"2020-04-10T11:29:22.824792","modified":"2022-09-26T09:08:12.732452","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Locus (Ensembl) contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_genelocus.csv","filename":"fruitfly_protein_genelocus.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"Drosophila_melanogaster.BDGP6.32.104.gtf","uri":"/data/shared/glyds/downloads/ucsc/gtf/Drosophila_melanogaster.BDGP6.32.104.gtf"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genelocus.csv","filename":"fruitfly_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genelocus.stat.csv","filename":"fruitfly_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000640/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c3ccbff6bc3db81160aa6df716f43d89"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:15.897000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000641/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Gene Names (UniProtKB)","version":"v-0.0.0","created":"","modified":"2024-05-17T11:24:07.596Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Names (UniProtKB) dataset contains UniProtKB gene Names/names for fruitfly [taxid:7227] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name).  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB gene Names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_genenames_uniprotkb.csv","filename":"fruitfly_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_genenames_uniprotkb.stat.csv","filename":"fruitfly_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000641/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2ef7cf0b2bc07a7b9917172336cc7ca03a2f7365d9883c65e44abd063ae6054b"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":400,"last_update":"2024-05-17T11:24:07.596037Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000641/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Gene Names (UniProtKB)","version":"v-2.0.2","created":"","modified":"2022-09-26T09:08:12.751848","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Names (UniProtKB) dataset contains UniProtKB gene Names/names for fruitfly [taxid:7227] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name).  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB gene Names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_genenames_uniprotkb.csv","filename":"fruitfly_protein_genenames_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_genenames_uniprotkb.csv","filename":"fruitfly_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_genenames_uniprotkb.stat.csv","filename":"fruitfly_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000641/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"082b310fbd13d0250f9cca4cbe06e72421931e681136423d7cb9f26e2b29f78a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.830000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000641/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Gene Names (UniProtKB)","version":"v-2.1.1","created":"","modified":"2022-09-26T09:08:12.751848","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Names (UniProtKB) dataset contains UniProtKB gene Names/names for fruitfly [taxid:7227] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name).  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB gene Names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_genenames_uniprotkb.csv","filename":"fruitfly_protein_genenames_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genenames_uniprotkb.csv","filename":"fruitfly_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genenames_uniprotkb.stat.csv","filename":"fruitfly_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000641/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"537d4a39c46a475b03fc14ed0a3ee426"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:16.090000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000642/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Gene Names (NCBI RefSeq)","version":"v-0.0.0","created":"2022-08-30T15:40:57.216837","modified":"2024-05-17T11:24:07.633Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] gene Names/names (primary gene name and gene synonyms)  from NCBI RefSeq database.  If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein gene names","NCBI RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the gene Names/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_genenames_refseq.csv","filename":"fruitfly_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_genenames_refseq.stat.csv","filename":"fruitfly_protein_genenames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000642/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"00a9cb4ebb333a61a454198e9f00db1af97cc2d69a72d6802c26bdea1a6dd646"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":244,"last_update":"2024-05-17T11:24:07.633282Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000642/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Gene Names (NCBI RefSeq)","version":"v-2.0.2","created":"2022-08-30T15:40:57.216837","modified":"2022-09-26T09:08:12.476226","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] gene Names/names (primary gene name and gene synonyms)  from NCBI RefSeq database.  If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein gene names","NCBI RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the gene Names/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_7227.gpff","filename":"refseq_protein_all_7227.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_genenames_refseq.csv","filename":"fruitfly_protein_genenames_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_genenames_refseq.csv","filename":"fruitfly_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_genenames_refseq.stat.csv","filename":"fruitfly_protein_genenames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000642/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9822ab66b005a1525e242bd8f7a96fd43f7779dbbd511f2d52bbce8b1c0ede88"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:03.928000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000642/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Gene Names (NCBI RefSeq)","version":"v-2.1.1","created":"2022-08-30T15:40:57.216837","modified":"2022-09-26T09:08:12.476226","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"","contribution":["contributedBy"],"name":"Not Applicable","email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] gene Names/names (primary gene name and gene synonyms)  from NCBI RefSeq database.  If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein gene names","NCBI RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the gene Names/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_7227.gpff","filename":"refseq_protein_all_7227.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_genenames_refseq.csv","filename":"fruitfly_protein_genenames_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genenames_refseq.csv","filename":"fruitfly_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genenames_refseq.stat.csv","filename":"fruitfly_protein_genenames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000642/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"90c04f4fec7e679afb5e92fa11d7a0fd"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:16.294000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000643/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly N-Glycosylation Sequon","version":"v-0.0.0","created":"2022-08-30T16:10:07.494670","modified":"2024-05-17T11:24:07.674Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for fruitfly [taxid:7227] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_glycosylation_motifs.csv","filename":"fruitfly_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_glycosylation_motifs.stat.csv","filename":"fruitfly_protein_glycosylation_motifs.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000643/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f1dd9f603f2f262a5144434c44f54d00be703a2345481b5b43096615fd394660","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2024-05-17T11:24:07.674035Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000643/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly N-Glycosylation Sequon","version":"v-2.0.2","created":"2022-08-30T16:10:07.494670","modified":"2022-09-26T09:08:12.486880","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for fruitfly [taxid:7227] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_canonicalsequences.fasta","filename":"fruitfly_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_glycosylation_motifs.csv","filename":"fruitfly_protein_glycosylation_motifs.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_glycosylation_motifs.csv","filename":"fruitfly_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_glycosylation_motifs.stat.csv","filename":"fruitfly_protein_glycosylation_motifs.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000643/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a65ba4c3f4e8152a387b0e23ffaaf8fb9f510c67a41c6007cbda036d396f89c0","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.703000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000643/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly N-Glycosylation Sequon","version":"v-2.1.1","created":"2022-08-30T16:10:07.494670","modified":"2022-09-26T09:08:12.486880","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for fruitfly [taxid:7227] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_canonicalsequences.fasta","filename":"fruitfly_protein_canonicalsequences.fasta"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_glycosylation_motifs.csv","filename":"fruitfly_protein_glycosylation_motifs.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"/data/shared/glyds/downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_glycosylation_motifs.csv","filename":"fruitfly_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_glycosylation_motifs.stat.csv","filename":"fruitfly_protein_glycosylation_motifs.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000643/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"28c5b946964bd25024450ffea6f1a04a","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:16.500000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000644/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Gene Ontology (GO)","version":"v-0.0.0","created":"2022-08-30T16:13:56.875825","modified":"2024-05-17T11:24:07.714Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Ontology (GO) dataset contains fruitfly [taxid:7227] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_go_annotation.csv","filename":"fruitfly_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_go_annotation.stat.csv","filename":"fruitfly_protein_go_annotation.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000644/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ff7d5054144cdf11358ca3c124921c7ecc6618bba8ce2e59e81de7453a125c0f","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":262,"last_update":"2024-05-17T11:24:07.714632Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000644/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Gene Ontology (GO)","version":"v-2.0.2","created":"2022-08-30T16:13:56.875825","modified":"2022-09-26T09:08:12.556119","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Ontology (GO) dataset contains fruitfly [taxid:7227] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_go_annotation.csv","filename":"fruitfly_protein_go_annotation.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_go_annotation.csv","filename":"fruitfly_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_go_annotation.stat.csv","filename":"fruitfly_protein_go_annotation.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000644/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"875a0d80e2b858c1eed9e89108698e27008268c0f746c49b8564b75a29b32424","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.042000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000644/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Gene Ontology (GO)","version":"v-2.1.1","created":"2022-08-30T16:13:56.875825","modified":"2022-09-26T09:08:12.556119","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Gene Ontology (GO) dataset contains fruitfly [taxid:7227] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_go_annotation.csv","filename":"fruitfly_protein_go_annotation.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_go_annotation.csv","filename":"fruitfly_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_go_annotation.stat.csv","filename":"fruitfly_protein_go_annotation.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000644/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"42b9fbe07ce1b26f6c3216f99602e13b","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:16.701000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000645/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Information (NCBI RefSeq)","version":"v-0.0.0","created":"2022-08-30T16:17:01.573604","modified":"2024-05-17T11:24:07.752Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Information (NCBI RefSeq) dataset contains Drosophila melanogaster [taxid:7227] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_info_refseq.csv","filename":"fruitfly_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_info_refseq.stat.csv","filename":"fruitfly_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000645/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"008bab8603145a131111c161127dbea0f01d33ca674b15819b6b8543eefdba31"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-05-17T11:24:07.752858Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000645/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Information (NCBI RefSeq)","version":"v-2.0.2","created":"2022-08-30T16:17:01.573604","modified":"2022-09-26T09:08:12.614356","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Information (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_7227.gpff","filename":"refseq_protein_all_7227.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_info_refseq.csv","filename":"fruitfly_protein_info_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_7227.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2022_02/refseq_protein_all_7227.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_info_refseq.csv","filename":"fruitfly_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_info_refseq.stat.csv","filename":"fruitfly_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000645/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"71970c32a09f635d4f2110efe282a55e89fe374ac8bab691e3c362984b80ad6a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.241000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000645/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Information (NCBI RefSeq)","version":"v-2.1.1","created":"2022-08-30T16:17:01.573604","modified":"2022-09-26T09:08:12.614356","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Information (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_7227.gpff","filename":"refseq_protein_all_7227.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_info_refseq.csv","filename":"fruitfly_protein_info_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_7227.gpff","uri":"/data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_7227.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_refseq.csv","filename":"fruitfly_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_refseq.stat.csv","filename":"fruitfly_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000645/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"719de877c85efeb75f69e85cf2a2bb25"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:16.891000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000646/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Information (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T16:19:56.970676","modified":"2024-05-17T11:24:07.792Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Information dataset contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_info_uniprotkb.csv","filename":"fruitfly_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_info_uniprotkb.stat.csv","filename":"fruitfly_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000646/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e86c75f5c8c8c613b763b8becd285e66264b36ed13820970d3b5606d97626b54"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":295,"last_update":"2024-05-17T11:24:07.792255Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000646/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Information (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T16:19:56.970676","modified":"2022-09-26T09:08:12.657372","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Information dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_info_uniprotkb.csv","filename":"fruitfly_protein_info_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_info_uniprotkb.csv","filename":"fruitfly_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_info_uniprotkb.stat.csv","filename":"fruitfly_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000646/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"af0421819e8e048a159bd27e5f98ac89d5740f9451f1175847c8e4eb90eb707b"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:40.729000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000646/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Information (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T16:19:56.970676","modified":"2022-09-26T09:08:12.657372","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Information dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_info_uniprotkb.csv","filename":"fruitfly_protein_info_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_uniprotkb.csv","filename":"fruitfly_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_uniprotkb.stat.csv","filename":"fruitfly_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000646/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ce2e635d8af4a391ece68d612677dffd"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:17.088000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000647/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Proteome Masterlist (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T16:22:11.325302","modified":"2024-05-17T11:24:07.835Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Proteome Masterlist dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_masterlist.stat.csv","filename":"fruitfly_protein_masterlist.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000647/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6dabcbf949e7fc75433e6efc827f9b27584ac3f4fba6bce39ed6476d9326d56e"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":364,"last_update":"2024-05-17T11:24:07.835486Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000647/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Proteome Masterlist (UniProtKB)","version":"v-2.0.2","created":"2022-08-30T16:22:11.325302","modified":"2022-09-26T09:08:12.709716","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Proteome Masterlist dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.stat.csv","filename":"fruitfly_protein_masterlist.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000647/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4b0f1a024196bd3b5bee08f040cb59abf8cd7386455ab7e1b640989d88c05df7"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:33.682000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000647/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Proteome Masterlist (UniProtKB)","version":"v-2.1.1","created":"2022-08-30T16:22:11.325302","modified":"2022-09-26T09:08:12.709716","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Proteome Masterlist dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.stat.csv","filename":"fruitfly_protein_masterlist.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000647/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"85acb6e18ddd082e82d2795000c7d45a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:17.288000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000648/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly EBI-UniProtKB NT file","version":"v-0.0.0","created":"2022-08-31T10:27:25.026993","modified":"2024-05-17T11:24:07.875Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly EBI-UniProtKB NT file contains proteome data for fruitfly [taxid:7227] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. T If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"step_number":0,"name":"","description":"The NT file requires no processing after it is received from EMBL-EBI-UniProtKB","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_ntdata.nt","filename":"fruitfly_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_ntdata.stat.csv","filename":"fruitfly_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000648/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"892782645991b1e777848e0da15cee010d47c1fccc763c26bc208abcd35eb29e"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":271,"last_update":"2024-05-17T11:24:07.875360Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000648/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly EBI-UniProtKB NT file","version":"v-2.0.2","created":"2022-08-31T10:27:25.026993","modified":"2022-09-26T09:08:12.581897","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly EBI-UniProtKB NT file contains proteome data for fruitfly [taxid:7227] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. T If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"step_number":0,"name":"","description":"The NT file requires no processing after it is received from EMBL-EBI-UniProtKB","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/fruitfly_protein_ntdata.nt","filename":"fruitfly_protein_ntdata.nt"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_ntdata.nt","filename":"fruitfly_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_ntdata.stat.csv","filename":"fruitfly_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000648/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b229c20d8db1099235625df0f7f4d382902e9e159c58b137604e473722a90b9b"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.613000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000648/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly EBI-UniProtKB NT file","version":"v-2.1.1","created":"2022-08-31T10:27:25.026993","modified":"2022-09-26T09:08:12.581897","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly EBI-UniProtKB NT file contains proteome data for fruitfly [taxid:7227] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. T If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"step_number":0,"name":"","description":"The NT file requires no processing after it is received from EMBL-EBI-UniProtKB","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/fruitfly_protein_ntdata.nt","filename":"fruitfly_protein_ntdata.nt"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_ntdata.nt","filename":"fruitfly_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_ntdata.stat.csv","filename":"fruitfly_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000648/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"568c6f8ae76a3f367b3cf59620b66eeb"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:17.481000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000649/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Names (NCBI RefSeq)","version":"v-0.0.0","created":"2022-08-31T10:35:44.201343","modified":"2024-05-17T11:24:07.914Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_proteinnames_refseq.csv","filename":"fruitfly_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_proteinnames_refseq.stat.csv","filename":"fruitfly_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000649/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6163e069a0e928a29703aea272585ce5c5b956d15f606b1b7b3ff30842cd709e"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":258,"last_update":"2024-05-17T11:24:07.914129Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000649/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Names (NCBI RefSeq)","version":"v-2.0.2","created":"2022-08-31T10:35:44.201343","modified":"2022-09-26T09:08:12.585707","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/refseq_protein_all_7227.gpff","filename":"refseq_protein_all_7227.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_info_refseq.csv","filename":"fruitfly_protein_info_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_proteinnames_refseq.csv","filename":"fruitfly_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_proteinnames_refseq.stat.csv","filename":"fruitfly_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000649/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1e408748e3cdf44c5c96986b070a0d7d22738863503a1fabbccd1c82e28465a1"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.448000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000649/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Names (NCBI RefSeq)","version":"v-2.1.1","created":"2022-08-31T10:35:44.201343","modified":"2022-09-26T09:08:12.585707","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/refseq_protein_all_7227.gpff","filename":"refseq_protein_all_7227.gpff"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_info_refseq.csv","filename":"fruitfly_protein_info_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_proteinnames_refseq.csv","filename":"fruitfly_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_proteinnames_refseq.stat.csv","filename":"fruitfly_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000649/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a2e2e227ec171ddc91a997fe785ed38b"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:17.679000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000650/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein PTM Annotation (UniProtKB)","version":"v-0.0.0","created":"2022-08-31T10:58:38.192589","modified":"2024-05-17T11:24:07.955Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein PTM Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000650/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ab8bb52a67f6b3f24891a78b5f67df910e236c45a09f61ce6fa257a2474557b6","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":318,"last_update":"2024-05-17T11:24:07.955379Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000650/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein PTM Annotation (UniProtKB)","version":"v-2.0.2","created":"2022-08-31T10:58:38.192589","modified":"2022-09-26T09:08:12.662574","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein PTM Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000650/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ffe94e195534eb97b220033fb2bf49257052588a084027a7b62604bba98d237a","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:36.586000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000650/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein PTM Annotation (UniProtKB)","version":"v-2.1.1","created":"2022-08-31T10:58:38.192589","modified":"2022-09-26T09:08:12.662574","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein PTM Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000650/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e01da30908b7bc21101f74bfcb48491f","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:17.873000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000651/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Recommended Names (UniProtKB)","version":"v-0.0.0","created":"2022-08-31T11:01:36.870249","modified":"2024-05-21T14:03:01.838Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Drosophila melanogaster [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","input_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_recnames.csv","filename":"fruitfly_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_recnames.stat.csv","filename":"fruitfly_protein_recnames.stat.csv"}}]},"error_domain":{},"object_id":"https://biocomputeobject.org/GLY_000651/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d504bdd09012a0fac22a63c50a322b29f7a9d99976ec76f0bc03da6b01724af3"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":237,"last_update":"2024-05-21T14:03:01.838843Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000651/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Recommended Names (UniProtKB)","version":"v-2.0.2","created":"2022-08-31T11:01:36.870249","modified":"2022-09-26T09:08:12.703732","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_recnames.csv","filename":"fruitfly_protein_recnames.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_recnames.csv","filename":"fruitfly_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_recnames.stat.csv","filename":"fruitfly_protein_recnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000651/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5cb7b693df8da5b260ce9bb58549ffa92901a1be29cb60c3eaeff044b6555fba"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.118000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000651/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Recommended Names (UniProtKB)","version":"v-2.1.1","created":"2022-08-31T11:01:36.870249","modified":"2022-09-26T09:08:12.703732","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_recnames.csv","filename":"fruitfly_protein_recnames.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_recnames.csv","filename":"fruitfly_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_recnames.stat.csv","filename":"fruitfly_protein_recnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000651/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c1a8eceeba36575b423bd220c39f6a71"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:18.077000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000652/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Sequence Info (UniProtKB)","version":"v-0.0.0","created":"2022-08-31T11:03:51.938138","modified":"2024-05-17T11:24:08.035Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Sequence Info (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_sequenceinfo.csv","filename":"fruitfly_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_sequenceinfo.stat.csv","filename":"fruitfly_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000652/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d2238fbcb9d90a00abd6c0ee5f5662e36c979e0b4e19b38a6f3af8b865462030"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":270,"last_update":"2024-05-17T11:24:08.035544Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000652/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Sequence Info (UniProtKB)","version":"v-2.0.2","created":"2022-08-31T11:03:51.938138","modified":"2022-09-26T09:08:12.552687","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Sequence Info (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_sequenceinfo.csv","filename":"fruitfly_protein_sequenceinfo.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_sequenceinfo.csv","filename":"fruitfly_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_sequenceinfo.stat.csv","filename":"fruitfly_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000652/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b777edc1f2bb0ae99e5926162edf75cb02a5e015acb85fb516d4ff6a22b83b67"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.620000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000652/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Sequence Info (UniProtKB)","version":"v-2.1.1","created":"2022-08-31T11:03:51.938138","modified":"2022-09-26T09:08:12.552687","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Sequence Info (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_sequenceinfo.csv","filename":"fruitfly_protein_sequenceinfo.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_sequenceinfo.csv","filename":"fruitfly_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_sequenceinfo.stat.csv","filename":"fruitfly_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000652/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8c0cf59325a179dddd3905f47a8e917f"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:18.291000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000653/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Signal Peptide","version":"v-0.0.0","created":"2022-08-31T11:05:56.022652","modified":"2024-06-03T22:35:55.463Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Signal Peptide dataset contains Drosophila melanogaster [taxid:7227] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. Signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. ","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_annotation.csv","filename":"fruitfly_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_peptidesequences.fasta","filename":"fruitfly_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_cleavedsequences.fasta","filename":"fruitfly_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_fullsequences.fasta","filename":"fruitfly_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_annotation.stat.csv","filename":"fruitfly_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_peptidesequences.stat.csv","filename":"fruitfly_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_cleavedsequences.stat.csv","filename":"fruitfly_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_signalp_fullsequences.stat.csv","filename":"fruitfly_protein_signalp_fullsequences.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000653/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bb3d2c4b591b9dba115542ca4dc046f969073aa5c2182bee274ef18d98993198"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":697,"last_update":"2024-06-03T22:35:55.463378Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000653/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Signal Peptide","version":"v-2.0.2","created":"2022-08-31T11:05:56.022652","modified":"2022-08-31T11:06:45.732251","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Signal Peptide dataset contains fruitfly [taxid:7227] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. Signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_annotation.csv","filename":"fruitfly_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_peptidesequences.fasta","filename":"fruitfly_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_cleavedsequences.fasta","filename":"fruitfly_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_fullsequences.fasta","filename":"fruitfly_protein_signalp_fullsequences.fasta"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_annotation.csv","filename":"fruitfly_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_peptidesequences.fasta","filename":"fruitfly_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_cleavedsequences.fasta","filename":"fruitfly_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_fullsequences.fasta","filename":"fruitfly_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_annotation.stat.csv","filename":"fruitfly_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_peptidesequences.stat.csv","filename":"fruitfly_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_cleavedsequences.stat.csv","filename":"fruitfly_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_signalp_fullsequences.stat.csv","filename":"fruitfly_protein_signalp_fullsequences.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000653/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"574a0c92ca61ec70369653eed6552450"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.608000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000653/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Signal Peptide","version":"v-2.1.1","created":"2022-08-31T11:05:56.022652","modified":"2022-08-31T11:06:45.732251","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Signal Peptide dataset contains fruitfly [taxid:7227] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. Signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_annotation.csv","filename":"fruitfly_protein_signalp_annotation.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_peptidesequences.fasta","filename":"fruitfly_protein_signalp_peptidesequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_cleavedsequences.fasta","filename":"fruitfly_protein_signalp_cleavedsequences.fasta"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_fullsequences.fasta","filename":"fruitfly_protein_signalp_fullsequences.fasta"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_annotation.csv","filename":"fruitfly_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_peptidesequences.fasta","filename":"fruitfly_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_cleavedsequences.fasta","filename":"fruitfly_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_fullsequences.fasta","filename":"fruitfly_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_annotation.stat.csv","filename":"fruitfly_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_peptidesequences.stat.csv","filename":"fruitfly_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_cleavedsequences.stat.csv","filename":"fruitfly_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_signalp_fullsequences.stat.csv","filename":"fruitfly_protein_signalp_fullsequences.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000653/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e9d3e16b2ccaa8edf1ca04bcbcf269dc"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:18.485000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000654/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Site Annotation","version":"v-0.0.0","created":"2022-08-31T11:08:19.037259","modified":"2024-05-17T11:24:08.115Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Site Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range.  If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_site_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000654/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"449f5d8c00d699a0a614f7a783c58805fd14509bd0db86298a538eea0d3bd431","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":310,"last_update":"2024-05-17T11:24:08.115426Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000654/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Site Annotation","version":"v-2.0.2","created":"2022-08-31T11:08:19.037259","modified":"2022-09-26T09:08:12.471396","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Site Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range.  If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_site_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000654/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3d0207a5f507b87f1554729affb9a03fde68cb4df46fa2bc475929166084750e","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.548000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000654/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Site Annotation","version":"v-2.1.1","created":"2022-08-31T11:08:19.037259","modified":"2022-09-26T09:08:12.471396","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Site Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range.  If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_site_annotation_uniprotkb.stat.csv","filename":"fruitfly_protein_site_annotation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000654/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"89c6ce3d7b86d563475b7eedf1229df5","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:18.695000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000655/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Submitted Names (UniProtKB)","version":"v-0.0.0","created":"2022-08-31T11:11:10.067141","modified":"2024-05-17T11:24:08.152Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for fruitfly [taxid:7227] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_submittednames.csv","filename":"fruitfly_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_submittednames.stat.csv","filename":"fruitfly_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000655/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"19157953c2a809975f2c8e8a79bfdf3b59bf969bc1e4145ff8a17ab34bce26e8"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":506,"last_update":"2024-05-17T11:24:08.152382Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000655/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Submitted Names (UniProtKB)","version":"v-2.0.2","created":"2022-08-31T11:11:10.067141","modified":"2022-09-26T09:08:12.491498","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for fruitfly [taxid:7227] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_submittednames.csv","filename":"fruitfly_protein_submittednames.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_submittednames.csv","filename":"fruitfly_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_submittednames.stat.csv","filename":"fruitfly_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000655/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dc531b0ac981f0c41fe72aa81f826cd500e47705d7053526e4c07aec86612ef0"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.324000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000655/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Submitted Names (UniProtKB)","version":"v-2.1.1","created":"2022-08-31T11:11:10.067141","modified":"2022-09-26T09:08:12.491498","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for fruitfly [taxid:7227] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_submittednames.csv","filename":"fruitfly_protein_submittednames.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_submittednames.csv","filename":"fruitfly_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_submittednames.stat.csv","filename":"fruitfly_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000655/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"665d3dc2ed40993c27feea4a3db3ffae"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:18.886000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000656/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000656/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"47e9ce7f03c20e95259c7e0d819e6680c69bb998cb60f1f6cfd0dc113152e793","provenance_domain":{"name":"Fruitfly Transcript Locus (Ensembl Transcript coordinates)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T11:17:02.109861","modified":"2025-11-04T12:30:11.894Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Transcript Locus (Ensembl Transcript coordinates) contains UniProtKB Drosophila melanogaster [taxid:7227] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Ensembl, and GlyGen. "],"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are mapped to ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file, and then maps any UniProtKB isoforms to the UniProtKB canonical accession. The transcript ID is then used to extract the transcript's chromosome, start position, end position and forward/reverse strand data from the Ensembl chromosomal gene annotation GTF file which has been converted to a TSV file. The extracted data is then used to create the csv dataset. ","input_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_transcriptlocus.csv","filename":"fruitfly_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_transcriptlocus.stat.csv","filename":"fruitfly_protein_transcriptlocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":497,"last_update":"2025-11-04T12:30:11.894751Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000656/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Transcript Locus (Ensembl Transcript coordinates)","version":"v-2.0.2","created":"2022-08-31T11:17:02.109861","modified":"2022-09-26T09:08:12.734263","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB fruitfly [taxid:7227] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlistcsv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_transcriptlocus.csv","filename":"fruitfly_protein_transcriptlocus.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_transcriptlocus.csv","filename":"fruitfly_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_transcriptlocus.stat.csv","filename":"fruitfly_protein_transcriptlocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000656/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d43f1a2e3583c0018f7d0c1cf5407240c1fe76cc02418fa96f952cb87f5d1994"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.638000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000656/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Transcript Locus (Ensembl Transcript coordinates)","version":"v-2.1.1","created":"2022-08-31T11:17:02.109861","modified":"2022-09-26T09:08:12.734263","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB fruitfly [taxid:7227] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlistcsv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_transcriptlocus.csv","filename":"fruitfly_protein_transcriptlocus.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_transcriptlocus.csv","filename":"fruitfly_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_transcriptlocus.stat.csv","filename":"fruitfly_protein_transcriptlocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000656/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e61564a142bd96bdbc2c09b5e82a7af3"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:19.077000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000657/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Bgee","version":"v-0.0.0","created":"2022-08-31T12:38:17.932566","modified":"2024-05-17T11:24:08.229Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Bgee dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_bgee.csv","filename":"fruitfly_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_bgee.stat.csv","filename":"fruitfly_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000657/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"99c9df48489917d034a8286941f0f1bfe1de8464a34ab49fd205b26e5ac36c34"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":471,"last_update":"2024-05-17T11:24:08.229941Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000657/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Bgee","version":"v-2.0.2","created":"2022-08-31T12:38:17.932566","modified":"2022-09-26T09:08:12.750012","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Bgee dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_bgee.csv","filename":"fruitfly_protein_xref_bgee.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_bgee.csv","filename":"fruitfly_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_bgee.stat.csv","filename":"fruitfly_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000657/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"948ab88c72eb470b305c9ac9bce4355b3e717ca4569c205ac76b4a81cf6b6ac4"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:44.808000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000657/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Bgee","version":"v-2.1.1","created":"2022-08-31T12:38:17.932566","modified":"2022-09-26T09:08:12.750012","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Bgee dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_bgee.csv","filename":"fruitfly_protein_xref_bgee.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_bgee.csv","filename":"fruitfly_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_bgee.stat.csv","filename":"fruitfly_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000657/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a442eb535bb0121aa2675184b82ea890"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:19.262000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000658/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref BRENDA","version":"v-0.0.0","created":"2022-08-31T12:42:59.923930","modified":"2024-05-17T11:24:08.268Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref BRENDA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_brenda.csv","filename":"fruitfly_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_brenda.stat.csv","filename":"fruitfly_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000658/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a9d517850d1435cf92b953a54a4cbeca2fe7d225c13fa50514dedbef081bc6ec"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":476,"last_update":"2024-05-17T11:24:08.268057Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000658/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref BRENDA","version":"v-2.0.2","created":"2022-08-31T12:42:59.923930","modified":"2022-09-26T09:08:12.451387","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref BRENDA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_brenda.csv","filename":"fruitfly_protein_xref_brenda.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_brenda.csv","filename":"fruitfly_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_brenda.stat.csv","filename":"fruitfly_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000658/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"70a178d6aa80df08701e41958d0dcfbe001406e9d02cef64e930c243be9afeaa"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.445000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000658/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref BRENDA","version":"v-2.1.1","created":"2022-08-31T12:42:59.923930","modified":"2022-09-26T09:08:12.451387","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref BRENDA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_brenda.csv","filename":"fruitfly_protein_xref_brenda.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_brenda.csv","filename":"fruitfly_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_brenda.stat.csv","filename":"fruitfly_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000658/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"659a109062a6caaca53ef0b1d2c29281"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:19.452000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000659/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref CAZy","version":"v-0.0.0","created":"2022-08-31T12:46:03.864774","modified":"2024-05-17T11:24:08.308Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref CAZy contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_cazy.csv","filename":"fruitfly_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_cazy.stat.csv","filename":"fruitfly_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000659/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"058bf283eecb8bb758e33116f21d7c4cec138315d25dc52bff43bfca86fdee53"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":465,"last_update":"2024-05-17T11:24:08.308354Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000659/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref CAZy","version":"v-2.0.2","created":"2022-08-31T12:46:03.864774","modified":"2022-09-26T09:08:12.533507","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref CAZy contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_cazy.csv","filename":"fruitfly_protein_xref_cazy.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_cazy.csv","filename":"fruitfly_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_cazy.stat.csv","filename":"fruitfly_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000659/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7ca9e80ae8327c41f52e475db77309b7bff5989ad75b4909bf8ded8268f63f57"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.700000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000659/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref CAZy","version":"v-2.1.1","created":"2022-08-31T12:46:03.864774","modified":"2022-09-26T09:08:12.533507","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref CAZy contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_cazy.csv","filename":"fruitfly_protein_xref_cazy.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_cazy.csv","filename":"fruitfly_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_cazy.stat.csv","filename":"fruitfly_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000659/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8aca64ba178af86bd5cc2848a61714a9"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:19.644000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000660/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref CDD","version":"v-0.0.0","created":"2022-08-31T12:47:56.887721","modified":"2024-05-17T11:24:08.347Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref CDD contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_cdd.csv","filename":"fruitfly_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_cdd.stat.csv","filename":"fruitfly_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000660/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c148f690018686bb60306d27fcb1380ab5a2475ade735d7cea2ddbe105c07bea"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2024-05-17T11:24:08.347595Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000660/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref CDD","version":"v-2.0.2","created":"2022-08-31T12:47:56.887721","modified":"2022-09-26T09:08:12.728533","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref CDD contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_cdd.csv","filename":"fruitfly_protein_xref_cdd.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_cdd.csv","filename":"fruitfly_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_cdd.stat.csv","filename":"fruitfly_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000660/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c55c6194dc4c2adca7c3fe5627527e41bd5edbc799f477a4b482bc9be5c095d6"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.638000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000660/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref CDD","version":"v-2.1.1","created":"2022-08-31T12:47:56.887721","modified":"2022-09-26T09:08:12.728533","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref CDD contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_cdd.csv","filename":"fruitfly_protein_xref_cdd.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_cdd.csv","filename":"fruitfly_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_cdd.stat.csv","filename":"fruitfly_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000660/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"381b3a3aa1804c3f1e99b0e3b911a47e"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:19.824000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000661/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref ChEMBL","version":"v-0.0.0","created":"2022-08-31T13:04:19.896737","modified":"2024-05-17T11:24:08.385Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref ChEMBL contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_chembl.csv","filename":"fruitfly_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_chembl.stat.csv","filename":"fruitfly_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000661/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"10a8f9b132a48b8234f92a4696611dccc2d9ea878e9a9dabae6ea9a6ab2be247"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-17T11:24:08.385146Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000661/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref ChEMBL","version":"v-2.0.2","created":"2022-08-31T13:04:19.896737","modified":"2022-09-26T09:08:12.756205","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref ChEMBL contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_chembl.csv","filename":"fruitfly_protein_xref_chembl.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_chembl.csv","filename":"fruitfly_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_chembl.stat.csv","filename":"fruitfly_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000661/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a845c9183e758c37e84668231e384999c714822db244a5e75384ae0921053e0c"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:14.894000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000661/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref ChEMBL","version":"v-2.1.1","created":"2022-08-31T13:04:19.896737","modified":"2022-09-26T09:08:12.756205","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref ChEMBL contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_chembl.csv","filename":"fruitfly_protein_xref_chembl.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_chembl.csv","filename":"fruitfly_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_chembl.stat.csv","filename":"fruitfly_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000661/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d7ddc619b1e9bd7130466f868f710474"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:20.009000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000662/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref NCBI Gene","version":"v-0.0.0","created":"2022-08-31T13:07:41.419400","modified":"2024-05-17T11:24:08.422Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref NCBI Gene dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_geneid.csv","filename":"fruitfly_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_geneid.stat.csv","filename":"fruitfly_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000662/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f299812fe213216e977c44d071f75f7497e65db856e2bbe6a1ac9cd992c6da52"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":505,"last_update":"2024-05-17T11:24:08.422721Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000662/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref NCBI Gene","version":"v-2.0.2","created":"2022-08-31T13:07:41.419400","modified":"2022-09-26T09:08:12.444004","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref NCBI Gene dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_geneid.csv","filename":"fruitfly_protein_xref_geneid.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_geneid.csv","filename":"fruitfly_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_geneid.stat.csv","filename":"fruitfly_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000662/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a90424f85acbfc4557d98748f916e09490607d1beefe210e62826c4a2deb81d4"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:37.559000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000662/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref NCBI Gene","version":"v-2.1.1","created":"2022-08-31T13:07:41.419400","modified":"2022-09-26T09:08:12.444004","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref NCBI Gene dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_geneid.csv","filename":"fruitfly_protein_xref_geneid.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_geneid.csv","filename":"fruitfly_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_geneid.stat.csv","filename":"fruitfly_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000662/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6fccef88d90ce91cfdee2ce1925e3f9f"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:20.205000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000663/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref IntAct","version":"v-0.0.0","created":"2022-08-31T13:13:10.878546","modified":"2024-05-17T11:24:08.461Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref IntAct dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_intact.csv","filename":"fruitfly_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_intact.stat.csv","filename":"fruitfly_protein_xref_intact.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000663/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7acf21006d0e36ef3db14e6fc5e0586c6c1a1219dc173689b1ac4771857baba0","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":529,"last_update":"2024-05-17T11:24:08.461479Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000663/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref IntAct","version":"v-2.0.2","created":"2022-08-31T13:13:10.878546","modified":"2022-09-26T09:08:12.540727","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref IntAct dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_intact.csv","filename":"fruitfly_protein_xref_intact.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_intact.csv","filename":"fruitfly_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_intact.stat.csv","filename":"fruitfly_protein_xref_intact.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000663/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"708bb3749e7da25eed2a9273e3dc5a164eca0bf815bd3e8e9554f097373e1714","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:32.413000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000663/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref IntAct","version":"v-2.1.1","created":"2022-08-31T13:13:10.878546","modified":"2022-09-26T09:08:12.540727","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref IntAct dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_intact.csv","filename":"fruitfly_protein_xref_intact.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_intact.csv","filename":"fruitfly_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_intact.stat.csv","filename":"fruitfly_protein_xref_intact.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000663/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"43f3d9043608e69a8bbd0c31b997f357","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:20.397000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000664/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref InterPro","version":"v-0.0.0","created":"2022-08-31T13:16:01.810293","modified":"2024-05-17T11:24:08.503Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref InterPro contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_interpro.csv","filename":"fruitfly_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_interpro.stat.csv","filename":"fruitfly_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000664/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2c96c46d36560eca7022ce475a980011d994ab323f0a4962128c120aed612bf2"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":463,"last_update":"2024-05-17T11:24:08.503509Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000664/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref InterPro","version":"v-2.0.2","created":"2022-08-31T13:16:01.810293","modified":"2022-09-26T09:08:12.565997","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref InterPro contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_interpro.csv","filename":"fruitfly_protein_xref_interpro.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_interpro.csv","filename":"fruitfly_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_interpro.stat.csv","filename":"fruitfly_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000664/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"913e0289c02dc9529768b091121305725755f6154d1c154a518e64793eb875ce"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:24.890000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000664/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref InterPro","version":"v-2.1.1","created":"2022-08-31T13:16:01.810293","modified":"2022-09-26T09:08:12.565997","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref InterPro contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_interpro.csv","filename":"fruitfly_protein_xref_interpro.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_interpro.csv","filename":"fruitfly_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_interpro.stat.csv","filename":"fruitfly_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000664/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"825bb173621a16d7ea109904ea431f07"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:20.588000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000665/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref KEGG PATHWAY","version":"v-0.0.0","created":"2022-08-31T13:17:32.978920","modified":"2024-05-17T11:24:08.545Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref KEGG PATHWAY contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_kegg.csv","filename":"fruitfly_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_kegg.stat.csv","filename":"fruitfly_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000665/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"af04c0280d934e29b209a5129e9ffbaf0aa21874b2deebe6d096a8ca31c96e70"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":408,"last_update":"2024-05-17T11:24:08.545441Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000665/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref KEGG PATHWAY","version":"v-2.0.2","created":"2022-08-31T13:17:32.978920","modified":"2022-09-26T09:08:12.598531","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref KEGG PATHWAY contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_kegg.csv","filename":"fruitfly_protein_xref_kegg.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_kegg.csv","filename":"fruitfly_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_kegg.stat.csv","filename":"fruitfly_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000665/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"aada2dff37c90cffeba34ab51cc9de0e40e0e4ff0a51f0244e8773b0a0d74d3c"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:43.637000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000665/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref KEGG PATHWAY","version":"v-2.1.1","created":"2022-08-31T13:17:32.978920","modified":"2022-09-26T09:08:12.598531","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref KEGG PATHWAY contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_kegg.csv","filename":"fruitfly_protein_xref_kegg.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_kegg.csv","filename":"fruitfly_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_kegg.stat.csv","filename":"fruitfly_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000665/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b839684cdfc54164591965133f48d715"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:20.783000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000666/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref OMA","version":"v-0.0.0","created":"2022-08-31T13:20:12.938783","modified":"2024-05-17T11:24:08.586Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref OMA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_oma.csv","filename":"fruitfly_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_oma.stat.csv","filename":"fruitfly_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000666/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"30ff5890659451a61326d9a08f2581f9acf02334bbe07d308b8132886d97806c"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":358,"last_update":"2024-05-17T11:24:08.586820Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000666/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref OMA","version":"v-2.0.2","created":"2022-08-31T13:20:12.938783","modified":"2022-09-26T09:08:12.686484","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref OMA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_oma.csv","filename":"fruitfly_protein_xref_oma.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_oma.csv","filename":"fruitfly_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_oma.stat.csv","filename":"fruitfly_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000666/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ec08ab4875adc8165fa6992f97f3788bf2a2273aa1d8c4ff1103879c81604bac"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:01.785000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000666/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref OMA","version":"v-2.1.1","created":"2022-08-31T13:20:12.938783","modified":"2022-09-26T09:08:12.686484","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref OMA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oma.csv","filename":"fruitfly_protein_xref_oma.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oma.csv","filename":"fruitfly_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oma.stat.csv","filename":"fruitfly_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000666/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"70b9a3a882624e88a6858c9d5a5213dd"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:20.974000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000667/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref OrthoDB","version":"v-0.0.0","created":"2022-08-31T13:25:53.921490","modified":"2024-05-17T11:24:08.626Z","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref OrthoDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_orthodb.csv","filename":"fruitfly_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_orthodb.stat.csv","filename":"fruitfly_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000667/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4614d5f9fa8aee88a0459514e535ef51629ade713ce9ba113536f27a31618790"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":424,"last_update":"2024-05-17T11:24:08.626735Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000667/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref OrthoDB","version":"v-2.0.2","created":"2022-08-31T13:25:53.921490","modified":"2022-09-26T09:08:12.688276","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref OrthoDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_orthodb.csv","filename":"fruitfly_protein_xref_orthodb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_orthodb.csv","filename":"fruitfly_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_orthodb.stat.csv","filename":"fruitfly_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000667/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f7f6d8335416a42c5e75263c1a062b0a9ca235de21005d57a466421c804bf3f7"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:55.399000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000667/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref OrthoDB","version":"v-2.1.1","created":"2022-08-31T13:25:53.921490","modified":"2022-09-26T09:08:12.688276","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref OrthoDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_orthodb.csv","filename":"fruitfly_protein_xref_orthodb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_orthodb.csv","filename":"fruitfly_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_orthodb.stat.csv","filename":"fruitfly_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000667/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8a35aef5de9deb9c91198a661d751458"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:21.173000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000668/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PANTHER","version":"v-0.0.0","created":"2022-08-31T13:34:27.210052","modified":"2024-05-17T11:24:08.669Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref PANTHER contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_panther.csv","filename":"fruitfly_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_panther.stat.csv","filename":"fruitfly_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000668/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e4ca7c513b8b22a0022e11fe265765d919aa80ade6dfa43306b5a5b3c191a008"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":463,"last_update":"2024-05-17T11:24:08.669503Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000668/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PANTHER","version":"v-2.0.2","created":"2022-08-31T13:34:27.210052","modified":"2022-09-26T09:08:12.543006","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref PANTHER contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_panther.csv","filename":"fruitfly_protein_xref_panther.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_panther.csv","filename":"fruitfly_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_panther.stat.csv","filename":"fruitfly_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000668/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9664ee1bd460aa590f5f3663e8666c3f6cda9eceac154ccd3b684e4c5583b642"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:00.532000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000668/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PANTHER","version":"v-2.1.1","created":"2022-08-31T13:34:27.210052","modified":"2022-09-26T09:08:12.543006","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref PANTHER contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_panther.csv","filename":"fruitfly_protein_xref_panther.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_panther.csv","filename":"fruitfly_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_panther.stat.csv","filename":"fruitfly_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000668/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c8130146ce7c9a61a7ea9367cd13e5c8"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:21.368000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000669/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PDB","version":"v-0.0.0","created":"2022-08-31T13:40:29.038163","modified":"2024-05-17T11:24:08.707Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref PDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_pdb.csv","filename":"fruitfly_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_pdb.stat.csv","filename":"fruitfly_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000669/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3bd61fde07ef748a51bc3fb5f72a75ecb8948408305b8b28e1a253c9620465e4"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2024-05-17T11:24:08.707255Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000669/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PDB","version":"v-2.0.2","created":"2022-08-31T13:40:29.038163","modified":"2022-09-26T09:08:12.651444","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref PDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pdb.csv","filename":"fruitfly_protein_xref_pdb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pdb.csv","filename":"fruitfly_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pdb.stat.csv","filename":"fruitfly_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000669/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"de7e1ba091f5f28adee579192ad95523abb2f90588251b8954636c929398fa04"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.872000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000669/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PDB","version":"v-2.1.1","created":"2022-08-31T13:40:29.038163","modified":"2022-09-26T09:08:12.651444","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref PDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pdb.csv","filename":"fruitfly_protein_xref_pdb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pdb.csv","filename":"fruitfly_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pdb.stat.csv","filename":"fruitfly_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000669/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0f14f6181b7401e2b87e198b437df521"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:21.550000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000670/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Pfam","version":"v-0.0.0","created":"2022-08-31T13:42:50.669379","modified":"2024-05-17T11:24:08.743Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Pfam contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_pfam.csv","filename":"fruitfly_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_pfam.stat.csv","filename":"fruitfly_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000670/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0761d1f432579af9490bca19bc174290a25f0473ef80002dbb460eb451571a3d"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":388,"last_update":"2024-05-17T11:24:08.743095Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000670/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Pfam","version":"v-2.0.2","created":"2022-08-31T13:42:50.669379","modified":"2022-09-26T09:08:12.679882","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Pfam contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pfam.csv","filename":"fruitfly_protein_xref_pfam.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pfam.csv","filename":"fruitfly_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pfam.stat.csv","filename":"fruitfly_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000670/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8fe2601bc6e81c0964b498200cb5cd17f0d9d36a8873ee5fb7e33afbe1ef3800"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.442000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000670/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Pfam","version":"v-2.1.1","created":"2022-08-31T13:42:50.669379","modified":"2022-09-26T09:08:12.679882","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Pfam contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pfam.csv","filename":"fruitfly_protein_xref_pfam.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pfam.csv","filename":"fruitfly_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pfam.stat.csv","filename":"fruitfly_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000670/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"26a28bb62743045b3070b3ad0f245536"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:21.741000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000671/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PRO","version":"v-0.0.0","created":"2022-08-31T13:44:37.770122","modified":"2024-05-17T11:24:08.782Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref PRO contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_pro.csv","filename":"fruitfly_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_pro.stat.csv","filename":"fruitfly_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000671/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9f3988e159c0b67d99391c15b932788fbfd8859d5d826cc619bf30fb70ee278f"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":387,"last_update":"2024-05-17T11:24:08.782033Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000671/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PRO","version":"v-2.0.2","created":"2022-08-31T13:44:37.770122","modified":"2022-09-26T09:08:12.692039","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref PRO contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pro.csv","filename":"fruitfly_protein_xref_pro.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pro.csv","filename":"fruitfly_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_pro.stat.csv","filename":"fruitfly_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000671/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c674e7bb2192e30cac7035c66f6d07ded61edec94599390143ea34b4d7921c56"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.415000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000671/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref PRO","version":"v-2.1.1","created":"2022-08-31T13:44:37.770122","modified":"2022-09-26T09:08:12.692039","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref PRO contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pro.csv","filename":"fruitfly_protein_xref_pro.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pro.csv","filename":"fruitfly_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_pro.stat.csv","filename":"fruitfly_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000671/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8bddada9c023951071daf25d9f0a29b8"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:21.931000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000672/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Reactome","version":"v-0.0.0","created":"2022-08-31T13:46:26.989814","modified":"2024-05-17T11:24:08.820Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Reactome contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_reactome.csv","filename":"fruitfly_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_reactome.stat.csv","filename":"fruitfly_protein_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000672/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ab5b0e191faeb4e2bce3e61ade9f6dd6230f8d1df201baa83de5db8b442a105d"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":346,"last_update":"2024-05-17T11:24:08.820220Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000672/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Reactome","version":"v-2.0.2","created":"2022-08-31T13:46:26.989814","modified":"2022-09-26T09:08:12.574776","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Reactome contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_reactome.csv","filename":"fruitfly_protein_xref_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_reactome.csv","filename":"fruitfly_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_reactome.stat.csv","filename":"fruitfly_protein_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000672/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c25667b5526de26c1d5d26fdb5296b08fb5616d45c1ac0d9ad3dd0e18a3671b9"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.321000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000672/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Reactome","version":"v-2.1.1","created":"2022-08-31T13:46:26.989814","modified":"2022-09-26T09:08:12.574776","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Reactome contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_reactome.csv","filename":"fruitfly_protein_xref_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_reactome.csv","filename":"fruitfly_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_reactome.stat.csv","filename":"fruitfly_protein_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000672/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8a89bb00f396f28663504986873c07f4"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:22.115000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000673/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000673/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"ccb929629233d5e8a9800414fe36fb4a3aae4ddab5db801c994602cd1c4e6948","provenance_domain":{"name":"Fruitfly UniProtKB Xref O-GlcNAc (MCW)","version":"v-0.0.0","license":"httpss://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:46:26.989814","modified":"2024-07-29T19:37:35.002Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly UniProtKB Xref O-GlcNAc (MCW) contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O - GlcNAc(MCW) is a database for O - GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["Drosophila","O-GlcNAc (MCW)","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oglcnac_mcw.csv","filename":"fruitfly_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oglcnac_mcw.stat.csv","filename":"fruitfly_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":362,"last_update":"2024-07-29T19:37:35.002571Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000673/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref O-GlcNAc (MCW)","version":"v-2.0.2","created":"2022-08-31T13:46:26.989814","modified":"2022-09-26T09:08:12.591263","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref O-GlcNAc (MCW) contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O - GlcNAc(MCW) is a database for O - GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Drosophila","O-GlcNAc (MCW)","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_oglcnac_db.csv","filename":"fruitfly_protein_xref_oglcnac_db.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_oglcnac_db.csv","filename":"fruitfly_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_oglcnac_db.stat.csv","filename":"fruitfly_protein_xref_oglcnac_db.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000673/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"27036f799b95dc8820d76b2780c464c30eec8417d9af315e9c7014eea77890dd"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:45.918000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000673/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref O-GlcNAc (MCW)","version":"v-2.1.1","created":"2022-08-31T13:46:26.989814","modified":"2022-09-26T09:08:12.591263","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref O-GlcNAc (MCW) contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O - GlcNAc(MCW) is a database for O - GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Drosophila","O-GlcNAc (MCW)","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oglcnac_db.csv","filename":"fruitfly_protein_xref_oglcnac_db.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oglcnac_db.csv","filename":"fruitfly_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oglcnac_db.stat.csv","filename":"fruitfly_protein_xref_oglcnac_db.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000673/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fbb66ec8c9df38a3fdcfaabce3481fd1"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:22.300000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000674/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref FlyBase","version":"v-0.0.0","created":"2022-09-01T11:43:42.773513","modified":"2024-05-17T11:24:08.899Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref FlyBase contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to FlyBase database accessions/identifiers.  If you use this dataset please provide proper attribution to FlyBase and GlyGen","FlyBase is a database for Drosophila gene and genomes. https://flybase.org/"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"FlyBase cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Drosophila","FlyBase","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to flybase database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_flybase.csv","filename":"fruitfly_protein_xref_flybase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_flybase.stat.csv","filename":"fruitfly_protein_xref_flybase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000674/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2c69cb6143ff201a789adb7a0fb1e971b02b93d00b38f3156bd8853434aff26e"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":314,"last_update":"2024-05-17T11:24:08.899674Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000674/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref FlyBase","version":"v-2.0.2","created":"2022-09-01T11:43:42.773513","modified":"2022-09-26T09:08:12.448259","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref FlyBase contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to FlyBase database accessions/identifiers.  If you use this dataset please provide proper attribution to FlyBase and GlyGen","FlyBase is a database for Drosophila gene and genomes. https://flybase.org/"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"FlyBase cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Drosophila","FlyBase","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to flybase database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_flybase.csv","filename":"fruitfly_protein_xref_flybase.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_flybase.csv","filename":"fruitfly_protein_xref_flybase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_flybase.stat.csv","filename":"fruitfly_protein_xref_flybase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000674/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3e60c3e36cc8004cc5e2e15e6f9179240d24b8d55a50519431c5d28ac921e146"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:35.726000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000674/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref FlyBase","version":"v-2.1.1","created":"2022-09-01T11:43:42.773513","modified":"2022-09-26T09:08:12.448259","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref FlyBase contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to FlyBase database accessions/identifiers.  If you use this dataset please provide proper attribution to FlyBase and GlyGen","FlyBase is a database for Drosophila gene and genomes. https://flybase.org/"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"FlyBase cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Drosophila","FlyBase","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to flybase database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_flybase.csv","filename":"fruitfly_protein_xref_flybase.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_flybase.csv","filename":"fruitfly_protein_xref_flybase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_flybase.stat.csv","filename":"fruitfly_protein_xref_flybase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000674/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"99d88f9d0d7c5fa892f68dc91e24557a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:22.475000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000675/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000675/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"76c73e55c0681e26e127d7ff05a99d93844d6eb84e26e16c3db57ed613893a2a","provenance_domain":{"name":"Fruitfly Proteoform Citations (GlyConnect)","version":"v-0.0.0","created":"2022-09-02T10:28:05.203794","modified":"2024-05-17T11:24:08.938Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file httpss://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (httpss://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":445,"last_update":"2024-05-17T11:24:08.938559Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000675/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Proteoform Citations (GlyConnect)","version":"v-2.0.2","created":"2022-09-02T10:28:05.203794","modified":"2022-09-26T09:08:12.538152","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file httpss://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (httpss://glyconnect.expasy.org/)."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_glyconnect.csv","filename":"fruitfly_proteoform_citations_glycosylation_glyconnect.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_glyconnect.csv","filename":"fruitfly_proteoform_citations_glycosylation_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_glyconnect.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_glyconnect.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000675/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"19911a5bd442791bc835732ddb4eb6eb2c6dd12fe21487d6b61251dd3a76dc36","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.810000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000675/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000675/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fb03221d25b4c4d3fd9afab01457c9c3","provenance_domain":{"name":"Fruitfly Proteoform Citations (GlyConnect)","version":"v-2.1.1","created":"2022-09-02T10:28:05.203794","modified":"2023-03-14T17:09:38.835Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file httpss://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (httpss://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:22.649000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000676/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000676/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d8005bdc6879af65b6a211ec68651afb3f0c62a8479cb50efccb4b0d275e252f","provenance_domain":{"name":"Fruitfly Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-0.0.0","created":"2022-09-02T10:30:49.524483","modified":"2024-05-17T11:24:08.976Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Fruitfly O-GlcNAc Glycosylation Sites (MCW)  httpss://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed","MCW","Glycosylation"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":242,"last_update":"2024-05-17T11:24:08.976336Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000676/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-2.0.2","created":"2022-09-02T10:30:49.524483","modified":"2022-09-26T09:08:12.719889","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Fruitfly O-GlcNAc Glycosylation Sites (MCW)  httpss://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed","MCW","Glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000676/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"300f6fc14a258484c8d5dc851657617a876ced72f997973cba6858ed747f971a","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.780000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000676/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000676/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dbce0a8bad946f3857995b0df98f93f3","provenance_domain":{"name":"Fruitfly Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-2.1.1","created":"2022-09-02T10:30:49.524483","modified":"2023-03-14T17:10:40.590Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Fruitfly O-GlcNAc Glycosylation Sites (MCW)  httpss://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed","MCW","Glycosylation"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:22.829000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000677/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000677/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"173cfca089ef32e7a7e054f9bf165b4444f00b550a870b940b776eb7a7309ee7","provenance_domain":{"name":"Fruitfly Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2022-09-02T10:55:15.390409","modified":"2024-05-17T11:24:09.016Z","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Proteoform Glycosylation Citations (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] citation details of the publications present in the dataset Fruitfly Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000681)."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","input_list":[]}]},"execution_domain":{"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":252,"last_update":"2024-05-17T11:24:09.016023Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000677/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.0.2","created":"2022-09-02T10:55:15.390409","modified":"2022-09-26T09:08:12.762186","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}],"output_list":[{"uri":"http://data.glygen.org/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_uniprotkb.csv","filename":"fruitfly_proteoform_citations_glycosylation_uniprotkb.csv"}]}]},"execution_domain":{"script":[],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_uniprotkb.csv","filename":"fruitfly_proteoform_citations_glycosylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_glycosylation_uniprotkb.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000677/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9685182ba40514fb894ef9bf2c47c20d0d24ecc1081f248067acdad2b1a68a8e","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:10.288000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000677/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000677/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f77cd4959c9c73931eb4f94e896fc721","provenance_domain":{"name":"Fruitfly Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.1.1","created":"2022-09-02T10:55:15.390409","modified":"2023-03-14T17:11:16.449Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Glycosylation"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}],"output_list":[{"uri":"http://data.glygen.org/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv"}]}]},"execution_domain":{"script":[],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:23.004000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000678/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000678/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dee8fad159bdc1151fe94aaf64fec2832f05e87a579b6989d072e4f69691dbd1","provenance_domain":{"name":"Fruitfly Proteoform Phosphorylation Citations (iPTMnet)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-02T13:26:18.780372","modified":"2024-12-05T19:38:57.798Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Proteoform Citations (iPTMNet) contains Drosophila melanogaster [taxid:7227] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","input_list":[]}],"keywords":["PMID","journal","citations","authors","iPTMnet","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":434,"last_update":"2024-12-05T19:38:57.798396Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000678/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Proteoform Phosphorylation Citations (iPTMnet)","version":"v-2.0.2","created":"2022-09-02T13:26:18.780372","modified":"2022-09-26T09:08:12.465052","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","iPTMnet","PubMed","Phosphorylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}],"output_list":[{"uri":"http://data.glygen.org/v-2.0.2/reviewed/fruitfly_proteoform_citations_phosphorylation_iptmnet.csv","filename":"fruitfly_proteoform_citations_phosphorylation_iptmnet.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_phosphorylation_iptmnet.csv","filename":"fruitfly_proteoform_citations_phosphorylation_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_phosphorylation_iptmnet.stat.csv","filename":"fruitfly_proteoform_citations_phosphorylation_iptmnet.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000678/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"35a790a87de80c791432b16ab1a698a5d21d78537425882c070987ef089b898a","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:12.545000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000678/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000678/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"161206ea2523890a0d6891d88bb2fba5","provenance_domain":{"name":"Fruitfly Proteoform Phosphorylation Citations (iPTMnet)","version":"v-2.1.1","created":"2022-09-02T13:26:18.780372","modified":"2023-03-14T17:11:57.540Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"description_domain":{"keywords":["PMID","journal","citations","authors","iPTMnet","PubMed","Phosphorylation"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}],"output_list":[{"uri":"http://data.glygen.org/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:23.196000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000679/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000679/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a3eb41efe9359a8b38869b6cfc3c22165778f59a769e559dcc92dc56b931e7e5","provenance_domain":{"name":"Fruitfly Proteoform Phosphorylation Citations (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-02T13:32:35.505543","modified":"2025-10-09T14:30:41.502Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The FruitFly Proteoform Phosphorylation Citations (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] publication information of phosphorylated glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","input_list":[]}],"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":379,"last_update":"2025-10-09T14:30:41.502201Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000679/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Proteoform Phosphorylation Citations (UniProtKB)","version":"v-2.0.2","created":"2022-09-02T13:32:35.505543","modified":"2022-09-26T09:08:12.502243","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}],"output_list":[{"uri":"http://data.glygen.org/v-2.0.2/reviewed/fruitfly_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"fruitfly_proteoform_citations_phosphorylation_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_phosphorylation_uniprotkb.csv","filename":"fruitfly_proteoform_citations_phosphorylation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_citations_phosphorylation_uniprotkb.stat.csv","filename":"fruitfly_proteoform_citations_phosphorylation_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000679/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"04fb205a124ba1f2c61d22468f1e402ea54a15d085ae73d67dbf798296c88e3e","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:52.245000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000679/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000679/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bb51eecd10c9c3d2abe068723364611b","provenance_domain":{"name":"Fruitfly Proteoform Phosphorylation Citations (UniProtKB)","version":"v-2.1.1","created":"2022-09-02T13:32:35.505543","modified":"2023-03-14T17:12:29.696Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}],"output_list":[{"uri":"http://data.glygen.org/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:23.400000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000681/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Glycosylation Sites (UniProtKB)","version":"v-0.0.0","created":"2022-09-06T09:50:57.220135","modified":"2024-05-17T11:24:09.136Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000681/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f57644f3e39a847d72f336419fca883b7d5f49e7ef2c0e7688cb6b23ddf3f102"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":291,"last_update":"2024-05-17T11:24:09.136684Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000681/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Glycosylation Sites (UniProtKB)","version":"v-2.0.2","created":"2022-09-06T09:50:57.220135","modified":"2022-09-26T09:08:12.457590","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000681/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b4405205af0a98bd7407e488edca7a60a324d6f85cd9107238ee8973cdcb8084"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:53.359000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000681/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Glycosylation Sites (UniProtKB)","version":"v-2.1.1","created":"2022-09-06T09:50:57.220135","modified":"2022-09-26T09:08:12.457590","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000681/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7af1f1a09efbda370e18a129e06424e2"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:23.585000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000682/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Phosphorylation Sites (UniProtKB)","version":"v-0.0.0","created":"2022-09-06T09:53:09.953304","modified":"2024-05-17T11:24:09.174Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Phosphorylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000682/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"663b8fa1c556de845f1912a6eb482ec853948dc8581a1fd6fc8ab1aeae7a712f","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":308,"last_update":"2024-05-17T11:24:09.174619Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000682/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Phosphorylation Sites (UniProtKB)","version":"v-2.0.2","created":"2022-09-06T09:53:09.953304","modified":"2022-09-26T09:08:12.741565","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Phosphorylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000682/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cc7a5efff9f464667a74a58e7202eeb72cb79d1da458b19f67cc17cf4645ea04","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:31.721000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000682/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Phosphorylation Sites (UniProtKB)","version":"v-2.1.1","created":"2022-09-06T09:53:09.953304","modified":"2022-09-26T09:08:12.741565","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Phosphorylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000682/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"38d7162a86bbf29416734a676891cce1","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:23.778000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000683/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Phosphorylation Sites (iPTMNet)","version":"v-0.0.0","created":"2022-09-06T09:56:04.354720","modified":"2024-05-21T14:47:19.888Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Phosphorylation Sites (iPTMNet) dataset contains Drosophila melanogaster [taxid:7227] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["iPTMnet","Phosphorylation sites"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","description":"The script extracts the phosphorylation information from the source dataset as per taxid and extracts as a csv dataset. The protein accession and sites are mapped to the UniProtKB canonical accession and fasta sequence.","version":"1","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000683/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e936733ee7346051508ffb7577b1d93b8e7afa4651c41481fa7c4c02b729a761","error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":307,"last_update":"2024-05-21T14:47:19.888764Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000683/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Phosphorylation Sites (iPTMNet)","version":"v-2.0.2","created":"2022-09-06T09:56:04.354720","modified":"2022-09-26T09:08:12.740578","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset contains fruitfly [taxid:7227] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["iPTMnet","Phosphorylation sites"],"pipeline_steps":[{"step_number":0,"name":"make-proteoform-dataset.py","description":"The script extracts the phosphorylation information from the source dataset as per taxid and extracts as a csv dataset. The protein accession and sites are mapped to the UniProtKB canonical accession and fasta sequence.","version":"1","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/ptm.txt","filename":"ptm.txt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"https:/data.glygen.org/ln2downloads/iptmnet/2022_02/ptm.txt"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"https:/data.glygen.org/ln2downloads/iptmnet/2022_02/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000683/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7535720e5c5a64f7336a898cc11d4fba6176666cd7b5fa8cc2fbea54e9eaef60","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:38.738000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000683/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Phosphorylation Sites (iPTMNet)","version":"v-2.1.1","created":"2022-09-06T09:56:04.354720","modified":"2022-09-26T09:08:12.740578","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset contains fruitfly [taxid:7227] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["iPTMnet","Phosphorylation sites"],"pipeline_steps":[{"step_number":0,"name":"make-proteoform-dataset.py","description":"The script extracts the phosphorylation information from the source dataset as per taxid and extracts as a csv dataset. The protein accession and sites are mapped to the UniProtKB canonical accession and fasta sequence.","version":"1","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/ptm.txt","filename":"ptm.txt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"/data/shared/glyds/downloads/iptmnet/2023_05_22/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000683/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"794a3214a9cf2e6f26d1a3a15cfea0da","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:23.968000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000684/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Glycosyltransferases","version":"v-0.0.0","created":"2022-09-06T11:20:50.205601","modified":"2024-05-17T11:24:09.252Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosyltransferases dataset contains a list of fruitfly [taxid:7227] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["GT","gycosyltransferase","CAZy"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_glycosyltransferase.csv","filename":"fruitfly_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_glycosyltransferase.stat.csv","filename":"fruitfly_protein_glycosyltransferase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000684/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"df42fff149d613bd476e9348e7f8a151874585e5ab7b24943c449ffc4ddacdff"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":293,"last_update":"2024-05-17T11:24:09.252127Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000684/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Glycosyltransferases","version":"v-2.0.2","created":"2022-09-06T11:20:50.205601","modified":"2022-09-26T09:08:12.697120","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosyltransferases dataset contains a list of fruitfly [taxid:7227] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["GT","gycosyltransferase","CAZy"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/fruitfly_protein_glycosyltransferase.csv","filename":"fruitfly_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_glycosyltransferase.csv","filename":"fruitfly_protein_glycosyltransferase.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/fruitfly_protein_glycosyltransferase.csv"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_glycosyltransferase.csv","filename":"fruitfly_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_glycosyltransferase.stat.csv","filename":"fruitfly_protein_glycosyltransferase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000684/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"eebd51d5b8474c44e7ba6529a61380606b75cce0167f278c6b4c4127d1e33227"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:42.547000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000684/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Glycosyltransferases","version":"v-2.1.1","created":"2022-09-06T11:20:50.205601","modified":"2022-09-26T09:08:12.697120","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycosyltransferases dataset contains a list of fruitfly [taxid:7227] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["GT","gycosyltransferase","CAZy"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/fruitfly_protein_glycosyltransferase.csv","filename":"fruitfly_protein_glycosyltransferase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_glycosyltransferase.csv","filename":"fruitfly_protein_glycosyltransferase.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/fruitfly_protein_glycosyltransferase.csv"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_glycosyltransferase.csv","filename":"fruitfly_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_glycosyltransferase.stat.csv","filename":"fruitfly_protein_glycosyltransferase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000684/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1dfed0434821a2929ded881111da1e75"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:24.159000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000685/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Glycohydrolases","version":"v-0.0.0","created":"2022-09-06T11:23:37.687653","modified":"2024-05-17T11:24:09.291Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycohydrolases dataset contains a list of fruitfly [taxid:7227] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_glycohydrolase.csv","filename":"fruitfly_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_glycohydrolase.stat.csv","filename":"fruitfly_protein_glycohydrolase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000685/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b57d688d4d97b912600ef36abfa1359ce2b22b525cc1506652eaa30b67091caa"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":283,"last_update":"2024-05-17T11:24:09.291164Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000685/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Glycohydrolases","version":"v-2.0.2","created":"2022-09-06T11:23:37.687653","modified":"2022-09-26T09:08:12.673905","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycohydrolases dataset contains a list of fruitfly [taxid:7227] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/fruitfly_protein_glycohydrolase.csv","filename":"fruitfly_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_glycohydrolase.csv","filename":"fruitfly_protein_glycohydrolase.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/fruitfly_protein_glycohydrolase.csv"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_glycohydrolase.csv","filename":"fruitfly_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_glycohydrolase.stat.csv","filename":"fruitfly_protein_glycohydrolase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000685/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"04ae7a53313b73f1aa1ea1e98afb8396a3f5405565df21fb38132be48214c369"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:25.369000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000685/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Glycohydrolases","version":"v-2.1.1","created":"2022-09-06T11:23:37.687653","modified":"2022-09-26T09:08:12.673905","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Glycohydrolases dataset contains a list of fruitfly [taxid:7227] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/fruitfly_protein_glycohydrolase.csv","filename":"fruitfly_protein_glycohydrolase.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_glycohydrolase.csv","filename":"fruitfly_protein_glycohydrolase.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/fruitfly_protein_glycohydrolase.csv"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_glycohydrolase.csv","filename":"fruitfly_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_glycohydrolase.stat.csv","filename":"fruitfly_protein_glycohydrolase.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000685/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"730d58211f54c4558609d4fb87c80e86"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:24.347000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000686/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Reactions (Reactome)","version":"v-0.0.0","created":"2022-09-06T11:25:28.437609","modified":"2024-05-17T11:24:09.328Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_reactions_reactome.csv","filename":"fruitfly_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_reactions_reactome.stat.csv","filename":"fruitfly_protein_reactions_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000686/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1a3f676dd3c0d5c28dc2713488cb9b30b3ebedc22c85b3479929c82c18b59cd2"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":336,"last_update":"2024-05-17T11:24:09.328261Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000686/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Reactions (Reactome)","version":"v-2.0.2","created":"2022-09-06T11:25:28.437609","modified":"2022-09-26T09:08:12.647223","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_reactome.csv","filename":"fruitfly_protein_reactions_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_reactome.csv","filename":"fruitfly_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_reactome.stat.csv","filename":"fruitfly_protein_reactions_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000686/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a3f3dd49f53d0bf8fa6cb4ceaf71294170d59c3a21562b6616cc1d6838fc9aa3"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:54.615000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000686/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Reactions (Reactome)","version":"v-2.1.1","created":"2022-09-06T11:25:28.437609","modified":"2022-09-26T09:08:12.647223","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_reactome.csv","filename":"fruitfly_protein_reactions_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_reactome.csv","filename":"fruitfly_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_reactome.stat.csv","filename":"fruitfly_protein_reactions_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000686/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bb5e2d8590ee7b9b0cb3d181389a9c91"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:24.519000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000687/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Reactions Rhea","version":"v-0.0.0","created":"2022-09-06T11:37:59.766468","modified":"2024-05-17T11:24:09.364Z","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reactions (Rhea) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen\""],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Reactions","Participants","Enzymes"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_reactions_rhea.csv","filename":"fruitfly_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_reactions_rhea.stat.csv","filename":"fruitfly_protein_reactions_rhea.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000687/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"763a0f6fcfc5c33af0574808fef4a8ae2991b73bbd78c936b73f12a8b1b57a25","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-17T11:24:09.364960Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000687/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Reactions Rhea","version":"v-2.0.2","created":"2022-09-06T11:37:59.766468","modified":"2022-09-26T09:08:12.541950","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reactions (Rhea) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen\""],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Reactions","Participants","Enzymes"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_rhea.csv","filename":"fruitfly_protein_reactions_rhea.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_rhea.csv","filename":"fruitfly_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_rhea.stat.csv","filename":"fruitfly_protein_reactions_rhea.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000687/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e5fa00983429c60017501708496d7cc697577dcb27e02d237d631213d5a2be32","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:02.791000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000687/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Reactions Rhea","version":"v-2.1.1","created":"2022-09-06T11:37:59.766468","modified":"2022-09-26T09:08:12.541950","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reactions (Rhea) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen\""],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Reactions","Participants","Enzymes"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_rhea.csv","filename":"fruitfly_protein_reactions_rhea.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_rhea.csv","filename":"fruitfly_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_rhea.stat.csv","filename":"fruitfly_protein_reactions_rhea.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000687/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fdadb917e0f76bc2012f6fd3ea379f4f","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:24.698000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000688/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Reaction Participants (Reactome)","version":"v-0.0.0","created":"2022-09-06T11:52:53.037427","modified":"2024-05-21T15:05:09.095Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Drosophila melanogaster [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_participants_reactome.csv","filename":"fruitfly_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_participants_reactome.stat.csv","filename":"fruitfly_protein_participants_reactome.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000688/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"67c82fd80d84a6d073ae686d191772cfca220065fdeae43cd41cecbd688cba72","error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":386,"last_update":"2024-05-21T15:05:09.095585Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000688/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Reaction Participants (Reactome)","version":"v-2.0.2","created":"2022-09-06T11:52:53.037427","modified":"2022-09-26T09:08:12.689154","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["\"The Fruitfly Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen\""],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_reactome.csv","filename":"fruitfly_protein_reactions_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"https:/data.glygen.org/ln2downloads/chebi/07_16_2021/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_participants_reactome.csv","filename":"fruitfly_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_participants_reactome.stat.csv","filename":"fruitfly_protein_participants_reactome.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000688/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a1a6a43688159a434b1544177d54b585a327bdb4a330a1441728507291dbf019","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:07.618000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000688/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Reaction Participants (Reactome)","version":"v-2.1.1","created":"2022-09-06T11:52:53.037427","modified":"2022-09-26T09:08:12.689154","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["\"The Fruitfly Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen\""],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_reactome.csv","filename":"fruitfly_protein_reactions_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"/data/shared/glyds/downloads/chebi/2023_05_19/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_participants_reactome.csv","filename":"fruitfly_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_participants_reactome.stat.csv","filename":"fruitfly_protein_participants_reactome.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000688/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7e84ed982b291d13487f29d4b0dd2dbd","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:24.877000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000689/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Reaction Participants (Rhea)","version":"v-0.0.0","created":"2022-09-06T12:06:00.142793","modified":"2024-05-17T11:24:09.443Z","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Participants","Reactions"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_participants_rhea.csv","filename":"fruitfly_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_participants_rhea.stat.csv","filename":"fruitfly_protein_participants_rhea.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000689/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f76bedd5faf2632ceb0650b0679fe0760015399a29b9d54e01ab488eda08c9fc","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":358,"last_update":"2024-05-17T11:24:09.443480Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000689/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Reaction Participants (Rhea)","version":"v-2.0.2","created":"2022-09-06T12:06:00.142793","modified":"2022-09-26T09:08:12.687423","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Participants","Reactions"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_reactions_rhea.csv","filename":"fruitfly_protein_reactions_rhea.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_participants_rhea.csv","filename":"fruitfly_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_participants_rhea.stat.csv","filename":"fruitfly_protein_participants_rhea.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000689/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"194c281f30daa3e29dbfa3e7192a0813f3ee75133a9ac18a7b89ec32e558dceb","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:59.405000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000689/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Reaction Participants (Rhea)","version":"v-2.1.1","created":"2022-09-06T12:06:00.142793","modified":"2022-09-26T09:08:12.687423","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Participants","Reactions"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_rhea.csv","filename":"fruitfly_protein_reactions_rhea.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_participants_rhea.csv","filename":"fruitfly_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_participants_rhea.stat.csv","filename":"fruitfly_protein_participants_rhea.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000689/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"866efcfcf750c23f36901a9360c25b27","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:25.064000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000690/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Pathways (Reactome)","version":"v-0.0.0","created":"2022-09-06T12:11:33.921445","modified":"2024-05-21T15:41:33.867Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Pathways (Reactome) dataset contains Drosophila melanogaster [taxid:7227] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","Reactome is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_pathways_reactome.csv","filename":"fruitfly_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_pathways_reactome.stat.csv","filename":"fruitfly_protein_pathways_reactome.stat.csv"}}]},"error_domain":{},"object_id":"https://biocomputeobject.org/GLY_000690/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"483a697890b2f855bf86d6bd08356fad280886d01a021532a97477b847a9014d"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":375,"last_update":"2024-05-21T15:41:33.867726Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000690/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Pathways (Reactome)","version":"v-2.0.2","created":"2022-09-06T12:11:33.921445","modified":"2022-09-26T09:08:12.630687","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset contains fruitfly [taxid:7227] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen","Reactome is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_pathways_reactome.csv","filename":"fruitfly_protein_pathways_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_pathways_reactome.csv","filename":"fruitfly_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_pathways_reactome.stat.csv","filename":"fruitfly_protein_pathways_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000690/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f74efd421552a6f75b2034bd4cf8965136f3de9b2606b53c3097198a224a82a9"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.905000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000690/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Pathways (Reactome)","version":"v-2.1.1","created":"2022-09-06T12:11:33.921445","modified":"2022-09-26T09:08:12.630687","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset contains fruitfly [taxid:7227] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen","Reactome is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_pathways_reactome.csv","filename":"fruitfly_protein_pathways_reactome.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_pathways_reactome.csv","filename":"fruitfly_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_pathways_reactome.stat.csv","filename":"fruitfly_protein_pathways_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000690/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"afa916c85813ae043851b4ff042f0852"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:25.246000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000691/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly Protein Binary Interactions (IntAct)","version":"v-0.0.0","created":"2022-09-06T12:13:07.540218","modified":"2024-05-17T11:24:09.519Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Binary Interaction (IntAct) dataset contains fruitfly [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"step_number":0,"name":"make-protein-dataset.py","description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_binary_interactions.csv","filename":"fruitfly_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_binary_interactions.stat.csv","filename":"fruitfly_protein_binary_interactions.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000691/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a257f214e8fe0bc7ab3802d86cce2cef87bd684d5ca525203e8b925161889ff6","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2024-05-17T11:24:09.519496Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000691/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly Protein Binary Interactions (IntAct)","version":"v-2.0.2","created":"2022-09-06T12:13:07.540218","modified":"2022-09-26T09:08:12.548920","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Binary Interaction (IntAct) dataset contains fruitfly [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"step_number":0,"name":"make-protein-dataset.py","description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_binary_interactions.csv","filename":"fruitfly_protein_binary_interactions.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_binary_interactions.csv","filename":"fruitfly_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_binary_interactions.stat.csv","filename":"fruitfly_protein_binary_interactions.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000691/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a810498ae19086659cf2675e3ded72936f745ef96a174837e214eabde96f80d1","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:04.858000Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000691/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly Protein Binary Interactions (IntAct)","version":"v-2.1.1","created":"2022-09-06T12:13:07.540218","modified":"2022-09-26T09:08:12.548920","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Binary Interaction (IntAct) dataset contains fruitfly [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"step_number":0,"name":"make-protein-dataset.py","description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_binary_interactions.csv","filename":"fruitfly_protein_binary_interactions.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_binary_interactions.csv","filename":"fruitfly_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_binary_interactions.stat.csv","filename":"fruitfly_protein_binary_interactions.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000691/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"007be632778aad966bf9a14f4abb83e2","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:25.425000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000692/DRAFT","contents":{"provenance_domain":{"name":"Glycan PubChem Xref Status","version":"v-0.0.0","created":"2022-09-06T16:07:55.305836","modified":"2024-05-17T11:24:09.560Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides cross-references status to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). The dataset allows to know whether a given GlyGen GlyTouCan has PubChem mapping or not."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem Xref Status","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The script checks all the GlyTouCan accession in masterlist for PubChem mapping. The mapped GlyTouCan accessions to PubChem CID and SID are then extracted in the csv. If the GlyTouCan to PubChem mapping exists then the pubchem_xref_exists is yes","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_pubchem_status.csv","filename":"glycan_pubchem_status.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_pubchem_status.stat.csv","filename":"glycan_pubchem_status.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000692/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"40f27b23c2965512ae439b0cd66c8d57ddafc522e026b6a4f61155fca598eff7","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2024-05-17T11:24:09.560523Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000692/v-2.0.2","contents":{"provenance_domain":{"name":"Glycan PubChem Xref Status","version":"v-2.0.2","created":"2022-09-06T16:07:55.305836","modified":"2022-09-26T09:08:12.699747","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides cross-references status to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). The dataset allows to know whether a given GlyGen GlyTouCan has PubChem mapping or not."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem Xref Status","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The script checks all the GlyTouCan accession in masterlist for PubChem mapping. The mapped GlyTouCan accessions to PubChem CID and SID are then extracted in the csv. If the GlyTouCan to PubChem mapping exists then the pubchem_xref_exists is yes","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/glycan_pubchem_status.csv","filename":"glycan_pubchem_status.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_pubchem_status.csv","filename":"glycan_pubchem_status.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_pubchem_status.stat.csv","filename":"glycan_pubchem_status.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000692/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a8338f4dd5e68d627ade803d0d648710efa6b4e455e0f8e7846331b8bf5198ec","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:47.121000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000692/v-2.1.1","contents":{"provenance_domain":{"name":"Glycan PubChem Xref Status","version":"v-2.1.1","created":"2022-09-06T16:07:55.305836","modified":"2022-09-26T09:08:12.699747","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset provides cross-references status to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). The dataset allows to know whether a given GlyGen GlyTouCan has PubChem mapping or not."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem Xref Status","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The script checks all the GlyTouCan accession in masterlist for PubChem mapping. The mapped GlyTouCan accessions to PubChem CID and SID are then extracted in the csv. If the GlyTouCan to PubChem mapping exists then the pubchem_xref_exists is yes","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/glycan_pubchem_status.csv","filename":"glycan_pubchem_status.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_pubchem_status.csv","filename":"glycan_pubchem_status.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_pubchem_status.stat.csv","filename":"glycan_pubchem_status.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000692/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"df1a8921f875fb13cd6dac72b93458c1","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:25.605000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000693/DRAFT","contents":{"provenance_domain":{"name":"Human UniProtKB Xref GDLPA","version":"v-0.0.0","created":"2022-09-06T16:17:53.681025","modified":"2024-05-17T11:24:09.598Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https: //creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Gene and Drug Landing Page Aggregator resource. If you use this dataset please provide proper attribution to Gene and Drug Landing Page Aggregator and GlyGen","Gene and Drug Landing Page Aggregator (GDLPA) has links to 53 gene, 18 variant and 19 drug repositories that provide direct links to gene and drug landing pages. You can search by gene or drug name and then choose the sites that contain knowledge about your gene or drug of interest. Resources supported by the NIH Common Fund are listed first and have the CFDE logo at their top right corner - https://cfde-gene-pages.cloud/."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GDLPA cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Gene and Drug Landing Page Aggregator","GDLPA","cross-references","gene","drug","CFDE"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the gene names from the dataset and maps to the GlyGen's UniProtKB canonical accessions to generate a csv dataset.","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_cfde_gdlpa.csv","filename":"human_protein_xref_cfde_gdlpa.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_cfde_gdlpa.stat.csv","filename":"human_protein_xref_cfde_gdlpa.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000693/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"aba45ac5c6517d46a770883594921d2a9522fb5b6918eb866478ef1a563d439f"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":674,"last_update":"2024-05-17T11:24:09.598330Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000693/v-2.0.2","contents":{"provenance_domain":{"name":"Human UniProtKB Xref GDLPA","version":"v-2.0.2","created":"2022-09-06T16:17:53.681025","modified":"2022-09-26T09:08:12.669053","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https: //creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Gene and Drug Landing Page Aggregator resource. If you use this dataset please provide proper attribution to Gene and Drug Landing Page Aggregator and GlyGen","Gene and Drug Landing Page Aggregator (GDLPA) has links to 53 gene, 18 variant and 19 drug repositories that provide direct links to gene and drug landing pages. You can search by gene or drug name and then choose the sites that contain knowledge about your gene or drug of interest. Resources supported by the NIH Common Fund are listed first and have the CFDE logo at their top right corner - https://cfde-gene-pages.cloud/."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GDLPA cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Gene and Drug Landing Page Aggregator","GDLPA","cross-references","gene","drug","CFDE"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the gene names from the dataset and maps to the GlyGen's UniProtKB canonical accessions to generate a csv dataset.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_protein_xref_cfde_gdlpa.csv","filename":"human_protein_xref_cfde_gdlpa.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_cfde_gdlpa.csv","filename":"human_protein_xref_cfde_gdlpa.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_cfde_gdlpa.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_xref_cfde_gdlpa.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_cfde_gdlpa.csv","filename":"human_protein_xref_cfde_gdlpa.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_cfde_gdlpa.stat.csv","filename":"human_protein_xref_cfde_gdlpa.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000693/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"277a72e3a0fc97cd27a201c82fcf299d0bb57ad09ea82dd41a2c783dccd8c19d"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:27.682000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000693/v-2.1.1","contents":{"provenance_domain":{"name":"Human UniProtKB Xref GDLPA","version":"v-2.1.1","created":"2022-09-06T16:17:53.681025","modified":"2022-09-26T09:08:12.669053","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https: //creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Gene and Drug Landing Page Aggregator resource. If you use this dataset please provide proper attribution to Gene and Drug Landing Page Aggregator and GlyGen","Gene and Drug Landing Page Aggregator (GDLPA) has links to 53 gene, 18 variant and 19 drug repositories that provide direct links to gene and drug landing pages. You can search by gene or drug name and then choose the sites that contain knowledge about your gene or drug of interest. Resources supported by the NIH Common Fund are listed first and have the CFDE logo at their top right corner - https://cfde-gene-pages.cloud/."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GDLPA cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Gene and Drug Landing Page Aggregator","GDLPA","cross-references","gene","drug","CFDE"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the gene names from the dataset and maps to the GlyGen's UniProtKB canonical accessions to generate a csv dataset.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/compiled/human_protein_xref_cfde_gdlpa.csv","filename":"human_protein_xref_cfde_gdlpa.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_cfde_gdlpa.csv","filename":"human_protein_xref_cfde_gdlpa.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_xref_cfde_gdlpa.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_protein_xref_cfde_gdlpa.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_cfde_gdlpa.csv","filename":"human_protein_xref_cfde_gdlpa.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_cfde_gdlpa.stat.csv","filename":"human_protein_xref_cfde_gdlpa.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000693/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3d75f5b507add25db43d28e6245ff588"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:25.782000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000694/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000694/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"37647409f998b99ebf35e99f9b4fef13b2ca016384c7d382d16d0ffad9879e62","provenance_domain":{"name":"Mouse Xref The O-GlcNAc Database","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T16:20:17.127842","modified":"2024-12-10T17:27:08.625Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Mouse Xref The O-GlcNAc Database contains Mus musculus [taxid:10090] UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions.","input_list":[]}],"keywords":["O-GlcNAc","PubMed"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_oglcnac_mcw.csv","filename":"mouse_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_oglcnac_mcw.stat.csv","filename":"mouse_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":181,"last_update":"2024-12-10T17:27:08.625512Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000694/v-2.0.2","contents":{"provenance_domain":{"name":"Mouse Xref The O-GlcNAc Database","version":"v-2.0.2","created":"2022-09-06T16:20:17.127842","modified":"2022-09-26T09:08:12.745628","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Mouse Xref The O-GlcNAc Database contains mouse (taxid:10090) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_o_glcnac_mcw.csv","filename":"mouse_proteoform_citations_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_oglcnac_db.csv","filename":"mouse_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_oglcnac_db.stat.csv","filename":"mouse_protein_xref_oglcnac_db.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000694/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"18f119d4e00a5b8acdf812d26624f86d7f1b7d5a6f0e1e82737e39414e15ca4a","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:29.457000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000694/v-2.1.1","contents":{"provenance_domain":{"name":"Mouse Xref The O-GlcNAc Database","version":"v-2.1.1","created":"2022-09-06T16:20:17.127842","modified":"2022-09-26T09:08:12.745628","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Mouse Xref The O-GlcNAc Database contains mouse (taxid:10090) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_o_glcnac_mcw.csv","filename":"mouse_proteoform_citations_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oglcnac_db.csv","filename":"mouse_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oglcnac_db.stat.csv","filename":"mouse_protein_xref_oglcnac_db.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000694/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3a468312888f5d851a49ebce2c7096c9","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:25.972000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000695/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000695/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5aba7bd54f354ebc369f1e7bab5683c0c5ef71a0b67e25d397bdb62f1b0589c3","provenance_domain":{"name":"Rat Xref The O-GlcNAc Database","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T16:46:47.904415","modified":"2024-12-10T17:43:13.406Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Rat Xref The O-GlcNAc Database contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions.","input_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_oglcnac_mcw.csv","filename":"rat_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_oglcnac_mcw.stat.csv","filename":"rat_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":185,"last_update":"2024-12-10T17:43:13.406100Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000695/v-2.0.2","contents":{"provenance_domain":{"name":"Rat Xref The O-GlcNAc Database","version":"v-2.0.2","created":"2022-09-06T16:46:47.904415","modified":"2022-09-26T09:08:12.737290","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Rat Xref The O-GlcNAc Database contains rat (taxid:10116) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_oglcnac_db.csv","filename":"rat_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_oglcnac_db.stat.csv","filename":"rat_protein_xref_oglcnac_db.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000695/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"826f6a6d669c3c7d560be7b419fa2a297bc020707c0ebdeb79d9590e47d19f48","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:34.665000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000695/v-2.1.1","contents":{"provenance_domain":{"name":"Rat Xref The O-GlcNAc Database","version":"v-2.1.1","created":"2022-09-06T16:46:47.904415","modified":"2022-09-26T09:08:12.737290","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Rat Xref The O-GlcNAc Database contains rat (taxid:10116) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oglcnac_db.csv","filename":"rat_protein_xref_oglcnac_db.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oglcnac_db.stat.csv","filename":"rat_protein_xref_oglcnac_db.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000695/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"156e7ded27cd5c359584c8921e08e936","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:26.161000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000696/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000696/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0efd1ae795ded76833e8be27a96e37e8e800b293bee68b3ae1135ac3b569a39b","provenance_domain":{"name":"Mouse Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-0.0.0","created":"2022-09-06T16:49:22.879070","modified":"2024-05-17T11:24:09.711Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Mouse O-GlcNAc Glycosylation Sites (MCW) contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":198,"last_update":"2024-05-17T11:24:09.711820Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000696/v-2.0.2","contents":{"provenance_domain":{"name":"Mouse Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-2.0.2","created":"2022-09-06T16:49:22.879070","modified":"2022-09-26T09:08:12.499977","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Mouse O-GlcNAc Glycosylation Sites (MCW) contributed by Stephanie Olivier's group."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"mouse_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"mouse_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv","filename":"mouse_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000696/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b94e661a9b844d9fbb521fc33f2bde256cde16a38f4ffcd1b883bba45f4e13b3","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:11.405000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000696/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000696/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"11122582b4d97794e13ef0ad2597047f","provenance_domain":{"name":"Mouse Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-2.1.1","created":"2022-09-06T16:49:22.879070","modified":"2023-03-14T17:13:05.482Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Mouse O-GlcNAc Glycosylation Sites (MCW) contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_o_glcnac_mcw.csv","filename":"mouse_proteoform_citations_glycosylation_sites_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:26.373000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000697/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000697/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2f2daf0c6b3cab6d682580cb105cbaa95bba94612cc7ddb0e47463938aee1c39","provenance_domain":{"name":"Rat Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T16:51:28.071892","modified":"2025-10-09T14:06:49.339Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Rat O-GlcNAc Glycosylation Sites (MCW) contributed by Stephanie Olivier's group."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","input_list":[]}],"keywords":["O-GlcNAc","Publications","Citations","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":237,"last_update":"2025-10-09T14:06:49.339828Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000697/v-2.0.2","contents":{"provenance_domain":{"name":"Rat Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-2.0.2","created":"2022-09-06T16:51:28.071892","modified":"2022-09-26T09:08:12.463560","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Rat O-GlcNAc Glycosylation Sites (MCW) contributed by Stephanie Olivier's group."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv","filename":"rat_proteoform_citations_glycosylation_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv","filename":"rat_proteoform_citations_glycosylation_o_glcnac_mcw.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000697/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"54789916b574829cadfeed007f42df9e42fff5a4d833c57d47017edda5ce39c5","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:49.199000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000697/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000697/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a4d5a81cb70dd719a66750832457dc87","provenance_domain":{"name":"Rat Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-2.1.1","created":"2022-09-06T16:51:28.071892","modified":"2023-03-14T17:13:49.489Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Rat O-GlcNAc Glycosylation Sites (MCW) contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_o_glcnac_mcw.csv","filename":"rat_proteoform_citations_glycosylation_sites_o_glcnac_mcw.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:26.561000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000698/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Rhea","version":"v-0.0.0","created":"2022-09-06T16:53:49.310443","modified":"2024-05-17T11:24:09.795Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Rhea contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_rhea.csv","filename":"fruitfly_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_rhea.stat.csv","filename":"fruitfly_protein_xref_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000698/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c75227b32e33cb72ccbc23c7aac7d3d9d755b56c0715dcfe49b618b3d6bcf857"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":249,"last_update":"2024-05-17T11:24:09.795599Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000698/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Rhea","version":"v-2.0.2","created":"2022-09-06T16:53:49.310443","modified":"2022-09-26T09:08:12.763780","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Rhea contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_rhea.csv","filename":"fruitfly_protein_xref_rhea.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_rhea.csv","filename":"fruitfly_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_rhea.stat.csv","filename":"fruitfly_protein_xref_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000698/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8aa969c203e8d703248b63b0f1dbe46608040079395cf76c0e349ce65dfb3c66"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:50.938000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000698/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref Rhea","version":"v-2.1.1","created":"2022-09-06T16:53:49.310443","modified":"2022-09-26T09:08:12.763780","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref Rhea contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_rhea.csv","filename":"fruitfly_protein_xref_rhea.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_rhea.csv","filename":"fruitfly_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_rhea.stat.csv","filename":"fruitfly_protein_xref_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000698/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"049ceefa66380776689f9915046d3aed"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:26.754000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000699/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T16:55:15.307877","modified":"2024-05-21T14:40:31.476Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly UniProtKB Xref (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_uniprotkb.csv","filename":"fruitfly_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_uniprotkb.stat.csv","filename":"fruitfly_protein_xref_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000699/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"30eb400be7f14d78c02562b02b42d73f54efc106a6a7591a9188634b080a1ad1","error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":268,"last_update":"2024-05-21T14:40:31.476147Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000699/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB xref UniProtKB","version":"v-2.0.2","created":"2022-09-06T16:55:15.307877","modified":"2022-09-26T09:08:12.721639","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_uniprotkb.csv","filename":"fruitfly_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_uniprotkb.stat.csv","filename":"fruitfly_protein_xref_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000699/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"310855064bd4424bb8f55052816046a7dad3ce6666fcd78c1b09baa41b42229e","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:13.287000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000699/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB xref UniProtKB","version":"v-2.1.1","created":"2022-09-06T16:55:15.307877","modified":"2022-09-26T09:08:12.721639","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_uniprotkb.csv","filename":"fruitfly_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_uniprotkb.stat.csv","filename":"fruitfly_protein_xref_uniprotkb.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000699/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fe80cb5ee36613667db3d692ee7a65df","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:26.950000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000700/DRAFT","contents":{"provenance_domain":{"name":"Protein Resource Ontology [Fruitfly]","version":"v-0.0.0","created":"2022-09-14T12:16:23.572102","modified":"2024-05-21T15:28:47.873Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for Drosophila melanogaster [taxid:7227] proteins. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_pro_annotation.csv","filename":"fruitfly_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_pro_annotation.stat.csv","filename":"fruitfly_protein_pro_annotation.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000700/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d8f25a9ee0f229b6ccd3c3d62c2f1e9860bc8513d63e302e868f76e55201b24d","error_domain":{}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":210,"last_update":"2024-05-21T15:28:47.873228Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000700/v-2.0.2","contents":{"provenance_domain":{"name":"Protein Resource Ontology [Fruitfly]","version":"v-2.0.2","created":"2022-09-14T12:16:23.572102","modified":"2022-09-26T09:08:12.615962","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for fruitfly [taxid:7227] proteins. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"step_number":0,"name":"","description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_pro_annotation.csv","filename":"fruitfly_protein_pro_annotation.csv"}]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"https:/data.glygen.org/ln2downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_pro_annotation.csv","filename":"fruitfly_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_pro_annotation.stat.csv","filename":"fruitfly_protein_pro_annotation.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000700/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"be25d2157f2b9ca65d9cc8e24ecf932558fa7f2724a17968a26dd7bfd54856ba","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:28.516000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000700/v-2.1.1","contents":{"provenance_domain":{"name":"Protein Resource Ontology [Fruitfly]","version":"v-2.1.1","created":"2022-09-14T12:16:23.572102","modified":"2022-09-26T09:08:12.615962","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for fruitfly [taxid:7227] proteins. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"step_number":0,"name":"","description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_pro_annotation.csv","filename":"fruitfly_protein_pro_annotation.csv"}]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"/data/shared/glyds/downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_pro_annotation.csv","filename":"fruitfly_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_pro_annotation.stat.csv","filename":"fruitfly_protein_pro_annotation.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000700/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8827a4332663c450f04cd3f9577d98ab","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:27.138000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000701/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref RefSeq","version":"v-0.0.0","created":"2022-09-14T12:24:23.479851","modified":"2024-05-17T11:24:09.911Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref RefSeq contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_refseq.stat.csv","filename":"fruitfly_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000701/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"767b355e7c949812298ad9172a3621afd8b6f99dd9bed9b69f021640f930e2c4"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":635,"last_update":"2024-05-17T11:24:09.911401Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000701/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref RefSeq","version":"v-2.0.2","created":"2022-09-14T12:24:23.479851","modified":"2022-09-26T09:08:12.557748","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref RefSeq contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.stat.csv","filename":"fruitfly_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000701/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"91f3355ff05669536eab066d7c019ab49b2f873f0076aaec4c7fb8b0aeba63bd"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:27:46.320000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000701/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly UniProtKB Xref RefSeq","version":"v-2.1.1","created":"2022-09-14T12:24:23.479851","modified":"2022-09-26T09:08:12.557748","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniprotKB Xref RefSeq contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-drosophila-melanogaster.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-drosophila-melanogaster.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.stat.csv","filename":"fruitfly_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000701/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"99912154dfa5a4ba8d42a9c2e0e0e8eb"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:27.328000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000702/DRAFT","contents":{"provenance_domain":{"name":"Fruitfly NCBI Protein Linkouts","version":"v-0.0.0","created":"2022-09-14T12:25:39.026264","modified":"2024-05-21T15:53:11.687Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly NCBI Protein Linkouts contains Drosophila melanogaster [taxid:7227] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_ncbi_linkouts.csv","filename":"fruitfly_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_ncbi_linkouts.stat.csv","filename":"fruitfly_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{},"object_id":"https://biocomputeobject.org/GLY_000702/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"78666bde32165db48439fb807ca5a59f08493a7084f5dd9f2746ffa0de2534a7"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":266,"last_update":"2024-05-21T15:53:11.687844Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000702/v-2.0.2","contents":{"provenance_domain":{"name":"Fruitfly NCBI Protein Linkouts","version":"v-2.0.2","created":"2022-09-14T12:25:39.026264","modified":"2022-09-26T09:08:12.707824","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly NCBI Protein Linkouts contains fruitfly [taxid:7227] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/v-2.0.2/reviewed/fruitfly_protein_ncbi_linkouts.csv","filename":"fruitfly_protein_ncbi_linkouts.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_ncbi_linkouts.csv","filename":"fruitfly_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_ncbi_linkouts.stat.csv","filename":"fruitfly_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000702/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"33206360f5b05686faac549d2cc4eac397578a663c5cbe112d493ec07e33603a"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:32:06.004000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000702/v-2.1.1","contents":{"provenance_domain":{"name":"Fruitfly NCBI Protein Linkouts","version":"v-2.1.1","created":"2022-09-14T12:25:39.026264","modified":"2022-09-26T09:08:12.707824","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly NCBI Protein Linkouts contains fruitfly [taxid:7227] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv","filename":"fruitfly_protein_xref_refseq.csv"}],"output_list":[{"uri":"https://data.glygen.org/v-2.1.1/reviewed/fruitfly_protein_ncbi_linkouts.csv","filename":"fruitfly_protein_ncbi_linkouts.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_ncbi_linkouts.csv","filename":"fruitfly_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_ncbi_linkouts.stat.csv","filename":"fruitfly_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_000702/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5a520bdd1744b9a750811030092d48c0"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:27.527000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000703/DRAFT","contents":{"provenance_domain":{"name":"Glycan Pathway GlycoTree","version":"v-0.0.0","created":"2022-09-14T12:37:04.198762","modified":"2024-05-17T11:24:09.990Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains pathway data for all N-glycans which are fully mapped to the GlycoTree framework. Each pathway specifies details for a particular reaction catalyzed by enzymes (UniProtKB Accession) which effect the associated glycan structures (GlyTouCan Accessions)."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Pathway GlycoTree","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Pathway","Glycotree"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The input file was downloaded from the source author and a python script was used to extract the following keys: glytoucan_ac,source,target,residue_id,residue_name,enzyme_uniprotkb_ac,enzyme_tax_name. The script also assigned the recommended enzyme taxonomy name based on the UniProtKB accession. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_pathway_glycotree.csv","filename":"glycan_pathway_glycotree.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_pathway_glycotree.stat.csv","filename":"glycan_pathway_glycotree.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000703/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"23f4dadacb058c942c24bad2220fc6ac93b19d619c9e2d8b4e42a14a87d08167","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":272,"last_update":"2024-05-17T11:24:09.990125Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000703/v-2.0.2","contents":{"provenance_domain":{"name":"Glycan Pathway GlycoTree","version":"v-2.0.2","created":"2022-09-14T12:37:04.198762","modified":"2022-09-26T09:08:12.656288","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains pathway data for all N-glycans which are fully mapped to the GlycoTree framework. Each pathway specifies details for a particular reaction catalyzed by enzymes (UniProtKB Accession) which effect the associated glycan structures (GlyTouCan Accessions)."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Pathway GlycoTree","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Pathway","Glycotree"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The input file was downloaded from the source author and a python script was used to extract the following keys: glytoucan_ac,source,target,residue_id,residue_name,enzyme_uniprotkb_ac,enzyme_tax_name. The script also assigned the recommended enzyme taxonomy name based on the UniProtKB accession. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https://data.glygen.org/ln2downloads/v-2.0.2/02_06_2022/allPaths.json","filename":"allPaths.json"}],"output_list":[{"uri":"https://data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_pathway_glycotree.csv","filename":"glycan_pathway_glycotree.csv"}]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"allPaths.json","uri":"https:/data.glygen.org/ln2downloads/sandbox/02_06_2022/allPaths.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_pathway_glycotree.csv","filename":"glycan_pathway_glycotree.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_pathway_glycotree.stat.csv","filename":"glycan_pathway_glycotree.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000703/v-2.0.2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c04cf3e5de050879de8b44bdd278858c5a1c8b721531eb4891d438ca3d968bed","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2022-09-26T14:31:58.217000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000703/v-2.1.1","contents":{"provenance_domain":{"name":"Glycan Pathway GlycoTree","version":"v-2.1.1","created":"2022-09-14T12:37:04.198762","modified":"2022-09-26T09:08:12.656288","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains pathway data for all N-glycans which are fully mapped to the GlycoTree framework. Each pathway specifies details for a particular reaction catalyzed by enzymes (UniProtKB Accession) which effect the associated glycan structures (GlyTouCan Accessions)."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Pathway GlycoTree","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Drosophila melanogaster"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Pathway","Glycotree"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The input file was downloaded from the source author and a python script was used to extract the following keys: glytoucan_ac,source,target,residue_id,residue_name,enzyme_uniprotkb_ac,enzyme_tax_name. The script also assigned the recommended enzyme taxonomy name based on the UniProtKB accession. ","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"},{"uri":"https://data.glygen.org/ln2downloads/v-2.1.1/02_06_2022/allPaths.json","filename":"allPaths.json"}],"output_list":[{"uri":"https://data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_pathway_glycotree.csv","filename":"glycan_pathway_glycotree.csv"}]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"allPaths.json","uri":"/data/shared/glyds/downloads/sandbox/05_17_2023/allPaths.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_pathway_glycotree.csv","filename":"glycan_pathway_glycotree.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_pathway_glycotree.stat.csv","filename":"glycan_pathway_glycotree.stat.csv"}}]},"object_id":"https://biocomputeobject.org/GLY_000703/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8b9baf9ac646d8b34b3a0a7e514e76f2","error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:27.734000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000705/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000705/DRAFT"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-02-23T10:14:10.377000Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000706/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000706/DRAFT"},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-02-23T10:14:10.649000Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000707/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000707/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"cf64b84fdac4755f2c7e20fea883546c451245f4900f9580dd11f2a0388fe7f7","provenance_domain":{"name":"Glycan Tool Support","version":"v-0.0.0","created":"2023-02-16T02:48:48.291Z","modified":"2024-05-17T11:24:10.105Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Nathan Edwards","contribution":["contributedBy","authoredBy"],"affiliation":"Georgetown University","email":"nje5@georgetown.edu","orcid":""},{"name":"Will York","contribution":["authoredBy"],"affiliation":"University of Georgia","email":"will@ccrc.uga.edu","orcid":""},{"name":"Robert Woods","contribution":["contributedBy"],"affiliation":"University of Georgia","email":"rwoods.glycam@gmail.com","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset indicates the tool support status of each GlyTouCan accession. The status is required for the GlyCan Detail API. The tools are sandbox, gnome, pdb, gnome_glygen, gnome_glygen_nglycans, gnome_glygen_oglycans, gnome_glycotree_nglycans, and gnome_glycotree_oglycans. PDB support for glycam 3D structures was provided by Rob Woods (Glycam/UGA). Sandbox support was provided by Will York (UGA) and Nathan Edwards (Georgetown). All other tool support data was provided by Nathan Edwards (Georgetown)."],"description_domain":{"keywords":["Glycan","Tool Support","Gnome","PDB","Sandbox","GlycoTree"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_toolsupport.csv","filename":"glycan_toolsupport.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_toolsupport.stat.csv","filename":"glycan_toolsupport.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2024-05-17T11:24:10.105202Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000707/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000707/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"73f87be377c23847b85ed360a27557c1","provenance_domain":{"name":"Glycan Tool Support","version":"v-2.1.1","created":"2023-02-16T02:48:48.291Z","modified":"2023-03-14T17:21:46.883Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Nathan Edwards","contribution":["contributedBy","authoredBy"],"affiliation":"Georgetown University","email":"nje5@georgetown.edu","orcid":""},{"name":"Will York","contribution":["authoredBy"],"affiliation":"University of Georgia","email":"will@ccrc.uga.edu","orcid":""},{"name":"Robert Woods","contribution":["contributedBy"],"affiliation":"University of Georgia","email":"rwoods.glycam@gmail.com","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset indicates the tool support status of each GlyTouCan accession. The status is required for the GlyCan Detail API. The tools are sandbox, gnome, pdb, gnome_glygen, gnome_glygen_nglycans, gnome_glygen_oglycans, gnome_glycotree_nglycans, and gnome_glycotree_oglycans. PDB support for glycam 3D structures was provided by Rob Woods (Glycam/UGA). Sandbox support was provided by Will York (UGA) and Nathan Edwards (Georgetown). All other tool support data was provided by Nathan Edwards (Georgetown)."],"description_domain":{"keywords":["Glycan","Tool Support","Gnome","PDB","Sandbox","GlycoTree"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":""}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"2022_05_24","uri":"/data/shared/glyds/downloads/glycam_3d/glycan/2022_05_24"}},{"uri":{"filename":"GlycoTree_NGlycans.valid-accessions.txt","uri":"/data/shared/glyds/downloads/gnome/05_17_2023/GlycoTree_NGlycans.valid-accessions.txt"}},{"uri":{"filename":"GlycoTree_OGlycans.valid-accessions.txt","uri":"/data/shared/glyds/downloads/gnome/05_17_2023/GlycoTree_OGlycans.valid-accessions.txt"}},{"uri":{"filename":"GlyGen_NGlycans.valid-accessions.txt","uri":"/data/shared/glyds/downloads/gnome/05_17_2023/GlyGen_NGlycans.valid-accessions.txt"}},{"uri":{"filename":"GlyGen_OGlycans.valid-accessions.txt","uri":"/data/shared/glyds/downloads/gnome/05_17_2023/GlyGen_OGlycans.valid-accessions.txt"}},{"uri":{"filename":"GlyGen.valid-accessions.txt","uri":"/data/shared/glyds/downloads/gnome/05_17_2023/GlyGen.valid-accessions.txt"}},{"uri":{"filename":"accessionlist.csv","uri":"/data/shared/glyds/downloads/sandbox/05_17_2023/accessionlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_toolsupport.csv","filename":"glycan_toolsupport.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_toolsupport.stat.csv","filename":"glycan_toolsupport.stat.csv"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:27.932000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000708/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000708/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"867d7c12367488b3862b3a46f8dc3769286f0b65f7c09b725ba4ef5e7158928a","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-12-05T18:52:18.536Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Homo sapeins (taxid:9606) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":[null,"O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":344,"last_update":"2024-12-05T18:52:18.536527Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000708/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000708/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0c131d61afccb10f918530e1e348107d","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-24T16:22:06.506Z","modified":"2023-03-06T20:13:06.619Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains human (taxid:9606) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"keywords":["","O-GlcNAc","Serine"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_info_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"ambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/ambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"unambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/unambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:18.452000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000709/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000709/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"03af82ececc8c80378d3e445f9eb0b8d7b3ebc3982df8fd095b9e476c2fabfe1","provenance_domain":{"name":"Mouse O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-12-03T18:17:12.877Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Mus musculus (taxid:10090) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":[null,"O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":345,"last_update":"2024-12-03T18:17:12.877847Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000709/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000709/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"969d1852fd98b40fbc99accf91cc7d0b","provenance_domain":{"name":"Mouse O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-24T16:22:06.506Z","modified":"2023-03-06T20:14:30.429Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains mouse (taxid:10090) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"keywords":["","O-GlcNAc","Serine"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"ambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/ambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"unambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/unambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:18.653000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000710/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000710/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"92513dc999bef9747a8f0d7bf4570ace13c68cebfed9038bb86ff007eaf5e923","provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-12-10T18:49:25.111Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Rattus norvegicus [taxid:10116] O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":[null,"O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2024-12-10T18:49:25.111034Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000710/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000710/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"955e8f9b2d1645cdf47bd983f31eca4f","provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-24T16:22:06.506Z","modified":"2023-03-06T20:15:01.311Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains rat (taxid:10116) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO"],"description_domain":{"keywords":["","O-GlcNAc","Serine"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_info_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"ambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/ambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"unambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/unambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:18.849000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000711/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000711/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b5f0626546fa1f5d2890484b9ef1097080ff49d999ab5a5ab22174d4fa5d71d1","provenance_domain":{"name":"Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-12-05T18:53:47.702Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Drosophila melanogaster (taxid:7227) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":[null,"O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-12-05T18:53:47.702023Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000711/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000711/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b90e27c8e01276e29f29060f2afd3dd6","provenance_domain":{"name":"Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-24T16:22:06.506Z","modified":"2023-03-06T20:15:27.506Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains fruitfly (taxid:7227) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"keywords":["","O-GlcNAc","Serine"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"ambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/ambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"unambiguous_sites_version_2.0.csv","uri":"/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/unambiguous_sites_version_2.0.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:19.041000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000712/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000712/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b8f418c243bc6ff4932c82a3503645c74e07309bb75e9606d016f0e55b812a81","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-0.0.0","created":"2023-02-27T21:08:01.227Z","modified":"2024-05-17T11:24:10.298Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Human O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000708, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":251,"last_update":"2024-05-17T11:24:10.298461Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000712/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000712/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7e055c9d62ac87c43f188151af94353a","provenance_domain":{"name":"Human O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-27T21:08:01.227Z","modified":"2023-03-06T20:15:55.384Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Human O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000708, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:30.669000Z","access_count":29},{"object_id":"https://biocomputeobject.org/GLY_000713/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000713/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7e5d0534cf7ecffd6ff6ffd0b12e89f605344f5d01ffe1c92a518c3381f99f66","provenance_domain":{"name":"Mouse O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-0.0.0","created":"2023-02-27T21:08:01.227Z","modified":"2024-05-17T11:24:10.336Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Mouse O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000709, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":251,"last_update":"2024-05-17T11:24:10.336815Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000713/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000713/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"436a24ab788dfedf7a66b0fe17af5458","provenance_domain":{"name":"Mouse O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-27T21:08:01.227Z","modified":"2023-03-06T20:16:31.984Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Mouse O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Mouse O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000709, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"doi_citations.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/doi_citations.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:30.849000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000714/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000714/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9900be941eb4fbfc3b8d5e979f2b5e85b6e2621272e2c926c45aba863f6dec46","provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-0.0.0","created":"2023-02-27T21:08:01.227Z","modified":"2024-05-17T11:24:10.375Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Rat O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000710, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":247,"last_update":"2024-05-17T11:24:10.375525Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000714/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000714/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"319d004bd71dd7b53efbc65cf1448398","provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-27T21:08:01.227Z","modified":"2023-03-06T20:16:58.406Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Rat O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000710, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:31.037000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000715/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000715/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a56bcecdbec113b6d612b0d9aa2fbf09be6d787586acdba7496da66191d2c4de","provenance_domain":{"name":"Fruitfly O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-0.0.0","created":"2023-02-27T21:08:01.227Z","modified":"2024-05-17T11:24:10.414Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000711, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":257,"last_update":"2024-05-17T11:24:10.414817Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000715/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000715/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7a5c6b26b1c59ed744d30bdb940f77fd","provenance_domain":{"name":"Fruitfly O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-2.1.1","created":"2023-02-27T21:08:01.227Z","modified":"2023-03-06T20:17:44.645Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000711, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:31.223000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000716/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000716/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"64b048b4904daf7126d068256ad3a0a8cf70b80fc9a969407725feca4b24ff7d","provenance_domain":{"name":"Human O-Glucosylation Glycosylation Sites","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-27T21:41:28.559Z","modified":"2025-03-19T20:52:12.445Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy","curatedBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Daniel Williamson","contribution":["authoredBy","contributedBy"],"affiliation":"CCRC, UGA","email":"daniel.williamson25@uga.edu"},{"name":"Robert S Haltiwanger","contribution":["createdAt","contributedBy"],"affiliation":"CCRC, UGA","email":"rhalti@uga.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human O-Gluc Glycosylation Sites datasets contain human (taxid:9606) O-Glucosylation sites from POGLUT2 and POGLUT3 which O-glucosylate multiple EGF repeats in fibrillin - 1, -2, and LTBP1 and promote secretion of fibrillin - 1 [PMID:34411563]. The data from this paper has been split into two datasets, one which contains experimental evidence of O-Gluc Glycosylation Sites (human_proteoform_glycosylation_sites_o_gluc.csv) and the other contains predicted O-gluc sites based on the consensus sequence identified in their study and a Prosite Prorule (human_proteoform_glycosylation_sites_o_gluc_predicted.csv). The GlyTouCan ID for O-Gluc is G71142DF and the consensus sequence for O-gluc glycosylation is C3-x-N-T-x-G-S-(FY)-x-C4. The responsible O-glucosyltransferases are POGLUT2 and POGLUT3. The experimental dataset also contains Glycosylation stoichiometry: The relative amount (percentage) of a glycoform is based on peptide signal intensity determined by mass spectrometry.","The dataset was generated in the lab of Robert S Haltiwanger by Daniel Williamson."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-Gluc modified residue against UniProtKB Canonical sequences."}],"keywords":[null,"O-Gluc","O-Glucosylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv","filename":"human_proteoform_glycosylation_sites_o_gluc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_o_gluc.stat.csv","filename":"human_proteoform_glycosylation_sites_o_gluc.stat.csv"}},{"mediatype":"csv","uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc_predicted.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_o_gluc_predicted.csv"}},{"mediatype":"csv","uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc_predicted.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_o_gluc_predicted.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glucosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":1286,"last_update":"2025-03-19T20:52:12.445065Z","access_count":16},{"object_id":"https://biocomputeobject.org/GLY_000716/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000716/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d135b3d6b3eb3b15e9e12a9540e3d652","provenance_domain":{"name":"Human O-Glucosylation Glycosylation Sites","version":"v-2.1.1","created":"2023-02-27T21:41:28.559Z","modified":"2023-03-03T02:07:18.965Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Daniel Williamson","contribution":["authoredBy","contributedBy"],"affiliation":"CCRC, UGA","email":"daniel.williamson25@uga.edu","orcid":""},{"name":"Robert S Haltiwanger","contribution":["createdAt","contributedBy"],"affiliation":"CCRC, UGA","email":"rhalti@uga.edu","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human O-Gluc Glycosylation Sites contains human (taxid:9606) O-Glucosylation sites from OGLUT2 and POGLUT3 O - glucosylate multiple EGF repeats in fibrillin - 1, -2, and LTBP1 and promote secretion of fibrillin - 1 [PMID:34411563] (experimental) and based on the consensus sequence the other sites (predicted) were detected using Prosite Prorule. The GlyTouCan ID for O-Gluc is G71142DF and the consensus sequence for O-gluc glycosylation is C3-x-N-T-x-G-S-(FY)-x-C4. The enzymes for o-glucosylation is POGLUT2 and POGLUT3. The dataset also contains Glycosylation stoichiometry: The relative amount (percentage) of a glycoform based on peptide signal intensity determined by mass spectrometry.","The dataset is generated in the lab of Robert S Haltiwanger by Daniel Williamson."],"description_domain":{"keywords":["","O-Gluc","O-Glucosylation"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-Gluc modified residue against UniProtKB Canonical sequences."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_o-gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/human_proteoform_glycosylation_sites_o-gluc.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv","filename":"human_proteoform_glycosylation_sites_o_gluc.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.stat.csv","filename":"human_proteoform_glycosylation_sites_o_gluc.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glucosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:19.708000Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000717/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000717/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2a461e3b124d6a77f9001725cb729938698fc0eda3b71a70869de04eb61e0c27","provenance_domain":{"name":"Human O-Glucosylation Glycosylation Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-28T15:39:52.735Z","modified":"2025-03-19T17:33:33.763Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy","curatedBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Daniel Williamson","contribution":["authoredBy","contributedBy"],"affiliation":"CCRC, UGA","email":"daniel.williamson25@uga.edu"},{"name":"Robert S Haltiwanger","contribution":["createdAt","contributedBy"],"affiliation":"CCRC, UGA","email":"rhalti@uga.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The O-Glucosylation Glycosylation Citations datasets contain details of the publications present in the Human O-Glucosylation Glycosylation Sites  experimental and predicted datasets https://data.glygen.org/GLY_000716, contributed by Daniel Williamson from Bob Haltiwanger's group. The data from this paper has been split into two datasets, one which contains details of the publications present in the experimental dataset (human_proteoform_citations_glycosylation_sites_o_gluc.csv) and the other contains publications present in the predicted dataset (human_proteoform_citations_glycosylation_sites_o_gluc_predicted.csv)"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}],"keywords":["O-Gluc","O-Glucosylation","Publications","Citations","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc.csv","filename":"human_proteoform_citations_glycosylation_sites_o_gluc.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_o_gluc.stat.csv"}},{"mediatype":"csv","uri":{"filename":"human_proteoform_citations_glycosylation_sites_o_gluc_predicted.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc_predicted.csv"}},{"mediatype":"csv","uri":{"filename":"human_proteoform_citations_glycosylation_sites_o_gluc_predicted.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc_predicted.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":751,"last_update":"2025-03-19T17:33:33.763993Z","access_count":12},{"object_id":"https://biocomputeobject.org/GLY_000717/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000717/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"88d6f516022e9cb8da14206008b81d41","provenance_domain":{"name":"Human O-Glucosylation Glycosylation Citations","version":"v-2.1.1","created":"2023-02-28T15:39:52.735Z","modified":"2023-02-28T16:13:51.772Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Daniel Williamson","contribution":["authoredBy","contributedBy"],"affiliation":"CCRC, UGA","email":"daniel.williamson25@uga.edu","orcid":""},{"name":"Robert S Haltiwanger","contribution":["createdAt","contributedBy"],"affiliation":"CCRC, UGA","email":"rhalti@uga.edu","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The O-Glucosylation Glycosylation Citations dataset contains details of the publication present in the dataset Human O-Glucosylation Glycosylation Sites https://data.glygen.org/GLY_000716, contributed by Daniel Williamson from Bob Haltiwanger's group."],"description_domain":{"keywords":["O-Gluc","O-Glucosylation","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc.csv","filename":"human_proteoform_citations_glycosylation_sites_o_gluc.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_o_gluc.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_o_gluc.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:19.928000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000718/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000718/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2edc87052d0e6eaca4912553acfbd1638021522adea04c2da3bd8e1c75396846","provenance_domain":{"name":"Human Glycan Interaction Data Citations (MatrixDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-28T20:56:50.670Z","modified":"2024-05-21T16:21:41.799Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Sylvie Ricard-Blum","affiliation":"MatrixDB","contribution":["contributedBy"],"email":"sylvie.ricard-blum@univ-lyon1.fr"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycan Interaction Data Citations (MatrixDB) contains details of the publication present in the Human Glycan Interaction Data (MatrixDB) dataset (https://data.glygen.org/GLY_000332)."],"description_domain":{"keywords":["MatrixDB","Glycan Interaction","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_matrixdb.csv","filename":"human_protein_citations_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_matrixdb.stat.csv","filename":"human_protein_citations_matrixdb.stat.csv"}}]},"parametric_domain":[{"value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycan Interaction Data Citations (MatrixDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":192,"last_update":"2024-05-21T16:21:41.799692Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000718/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000718/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2313c28cf7a695c259ffd70e675d5381","provenance_domain":{"name":"The Human Glycan Interaction Data Citations (MatrixDB)","version":"v-2.1.1","created":"2023-02-28T20:56:50.670Z","modified":"2023-02-28T20:57:01.649Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Sylvie Ricard-Blum","affiliation":"MatrixDB","contribution":["contributedBy"],"email":"sylvie.ricard-blum@univ-lyon1.fr"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Glycan Interaction data Citations (MatrixDB)] contains details of the publication present in the dataset The Human Glycan Interaction data Citations (MatrixDB) https://data.glygen.org/GLY_000332."],"description_domain":{"keywords":["MatrixDB","Glycan Interaction","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_matrixdb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_matrixdb.csv","filename":"human_protein_citations_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_matrixdb.stat.csv","filename":"human_protein_citations_matrixdb.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycan Interaction Data Citations (MatrixDB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:31.811000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000719/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000719/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dd4605798225037ed4fb057b0cbd3044ed9a0a1e84cdf8ed2d0c8a0654699810","provenance_domain":{"name":"Mouse Glycan Interaction Data Citations (MatrixDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T16:22:39.632Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Sylvie Ricard-Blum","affiliation":"MatrixDB","contribution":["contributedBy"],"email":"sylvie.ricard-blum@univ-lyon1.fr"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycan Interaction Data Citations (MatrixDB) dataset contains details of the publication present in the Mouse Glycan Interaction Data (MatrixDB) dataset (https://data.glygen.org/GLY_000333)."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycan Interaction Data Citations (MatrixDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["MatrixDB","Glycan Interaction","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_citations_matrixdb.csv","filename":"mouse_protein_citations_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_citations_matrixdb.stat.csv","filename":"mouse_protein_citations_matrixdb.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":200,"last_update":"2024-05-21T16:22:39.632869Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000719/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000719/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"260df822c938f45ba7d9ce59c139f79d","provenance_domain":{"name":"The Mouse Glycan Interaction data Citations (MatrixDB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Sylvie Ricard-Blum","affiliation":"MatrixDB","contribution":["contributedBy"],"email":"sylvie.ricard-blum@univ-lyon1.fr"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}]},"usability_domain":["The Mouse Glycan Interaction data Citations (MatrixDB)] contains details of the publication present in the dataset The Mouse Glycan Interaction data Citations (MatrixDB) https://data.glygen.org/GLY_000333."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycan Interaction Data Citations (MatrixDB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["MatrixDB","Glycan Interaction","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_matrixdb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_matrixdb.csv","filename":"mouse_protein_citations_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_citations_matrixdb.stat.csv","filename":"mouse_protein_citations_matrixdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:31.993000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000720/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000720/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b4cb7fb32fe7a76da2ad3ac7a39e0b2f264e200c11da81f0429693c139088811","provenance_domain":{"name":"The Rat Glycan Interaction data Citations (MatrixDB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:10.604Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Sylvie Ricard-Blum","affiliation":"MatrixDB","contribution":["contributedBy"],"email":"sylvie.ricard-blum@univ-lyon1.fr"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycan Interaction data Citations (MatrixDB)] contains details of the publication present in the dataset The Rat Glycan Interaction data Citations (MatrixDB) https://data.glygen.org/GLY_000334."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycan Interaction Data Citations (MatrixDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["MatrixDB","Glycan Interaction","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_citations_matrixdb.csv","filename":"rat_protein_citations_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_citations_matrixdb.stat.csv","filename":"rat_protein_citations_matrixdb.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":201,"last_update":"2024-05-17T11:24:10.604934Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000720/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000720/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d62cb68cde726351056e2c34e49b1eea","provenance_domain":{"name":"The Rat Glycan Interaction data Citations (MatrixDB)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Sylvie Ricard-Blum","affiliation":"MatrixDB","contribution":["contributedBy"],"email":"sylvie.ricard-blum@univ-lyon1.fr"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}]},"usability_domain":["The Rat Glycan Interaction data Citations (MatrixDB)] contains details of the publication present in the dataset The Rat Glycan Interaction data Citations (MatrixDB) https://data.glygen.org/GLY_000334."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycan Interaction Data Citations (MatrixDB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["MatrixDB","Glycan Interaction","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_matrixdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_matrixdb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_matrixdb.csv","filename":"rat_protein_citations_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_citations_matrixdb.stat.csv","filename":"rat_protein_citations_matrixdb.stat.csv"}}]}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:32.178000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000721/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000721/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9b41b405410155fbcf2f351fa14b4bb8e278b3862e0483686d29a9ee37aabb55","provenance_domain":{"name":"Human Somatic Mutation Citations","version":"v-0.0.0","created":"","modified":"2024-05-17T11:24:10.644Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Somatic Mutation Citations contains details of the publication present in the dataset Human Somatic Mutation https://data.glygen.org/GLY_000462."],"description_domain":{"keywords":["Somatic","Mutation","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_mutation_somatic.csv","filename":"human_protein_citations_mutation_somatic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_mutation_somatic.stat.csv","filename":"human_protein_citations_mutation_somatic.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutation Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":154,"last_update":"2024-05-17T11:24:10.644579Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000721/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000721/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c1fc46d8c0519970450951217a3fa083","provenance_domain":{"name":"Human Somatic Mutation Citations","version":"v-2.1.1","created":"","modified":"","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Somatic Mutation Citations contains details of the publication present in the dataset Human Somatic Mutation https://data.glygen.org/GLY_000462."],"description_domain":{"keywords":["Somatic","Mutation","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_mutation_somatic.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_somatic.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_somatic.csv","filename":"human_protein_citations_mutation_somatic.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_somatic.stat.csv","filename":"human_protein_citations_mutation_somatic.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutation Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:32.367000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000722/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000722/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"51e72ebf49596d8370bde53f4fb101aca6bb8d25f4c1696692fa83a97b76f7de","provenance_domain":{"name":"Human Literature Mutations Citations","version":"v-0.0.0","created":"","modified":"2024-05-17T11:24:10.684Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Literature Mutations Citations contains details of the publication present in the dataset Human Literature Mutations https://data.glygen.org/GLY_000463."],"description_domain":{"keywords":["Literature","Mutation","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_mutation_literature.csv","filename":"human_protein_citations_mutation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_mutation_literature.stat.csv","filename":"human_protein_citations_mutation_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Literature Mutation Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":162,"last_update":"2024-05-17T11:24:10.684566Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000722/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000722/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a87ff8e9ae663fec3e00d44f269e33bf","provenance_domain":{"name":"Human Literature Mutations Citations","version":"v-2.1.1","created":"","modified":"","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Literature Mutations Citations contains details of the publication present in the dataset Human Literature Mutations https://data.glygen.org/GLY_000463."],"description_domain":{"keywords":["Literature","Mutation","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_mutation_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_literature.csv","filename":"human_protein_citations_mutation_literature.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_literature.stat.csv","filename":"human_protein_citations_mutation_literature.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Literature Mutation Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:32.550000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000723/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000723/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"54e7542b7307fe85bcd5f9e824d72e919d3c71d57c625862b1c42b58ad51c3d7","provenance_domain":{"name":"Human Xref O-GlcNAcAtlas","version":"v-0.0.0","created":"","modified":"2024-05-17T11:24:10.721Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Human Xref O-GlcNAcAtlas dataset contains human (taxid: 9606) UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"description_domain":{"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_oglcnac_atlas.csv","filename":"human_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_oglcnac_atlas.stat.csv","filename":"human_protein_xref_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":132,"last_update":"2024-05-17T11:24:10.721600Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000723/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000723/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4bd1fc43b9697ab90c426e34eab07ca7","provenance_domain":{"name":"Human Xref O-GlcNAcAtlas","version":"v-2.1.1","created":"","modified":"","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Human Xref O-GlcNAcAtlas dataset contains human (taxid: 9606) UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"description_domain":{"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oglcnac_atlas.csv","filename":"human_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oglcnac_atlas.stat.csv","filename":"human_protein_xref_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:32.731000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000724/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000724/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6c16acbcd1c16c21e6a6d77bf2eb5b6137e45084bdd9f083fa4d63334f590c06","provenance_domain":{"name":"Mouse Xref O-GlcNAcAtlas","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:28:41.361Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Mouse Xref O-GlcNAcAtlas dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}],"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_oglcnac_atlas.csv","filename":"mouse_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_oglcnac_atlas.stat.csv","filename":"mouse_protein_xref_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":171,"last_update":"2024-12-10T17:28:41.361465Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000724/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000724/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1f6af04e93344f838b5a7e4b4479f749","provenance_domain":{"name":"Mouse Xref O-GlcNAcAtlas","version":"v-2.1.1","created":"","modified":"","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Mouse Xref O-GlcNAcAtlas dataset contains mouse (taxid: 10090) UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"description_domain":{"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oglcnac_atlas.csv","filename":"mouse_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oglcnac_atlas.stat.csv","filename":"mouse_protein_xref_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:32.935000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000725/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000725/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7af059be4db168a5f6043f1b0b3fcb8772e71ead0420b5433644cfef95c665fc","provenance_domain":{"name":"Rat Xref O-GlcNAcAtlas","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:44:19.914Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Rat Xref O-GlcNAcAtlas dataset contains Rattus norvegicus [taxid: 10116] UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}],"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_oglcnac_atlas.csv","filename":"rat_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_oglcnac_atlas.stat.csv","filename":"rat_protein_xref_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":176,"last_update":"2024-12-10T17:44:19.914695Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000725/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000725/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7459bd1ea8342b91cd507f8967b0ce36","provenance_domain":{"name":"Rat Xref O-GlcNAcAtlas","version":"v-2.1.1","created":"","modified":"","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Rat Xref O-GlcNAcAtlas dataset contains rat (taxid: 10116) UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"description_domain":{"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oglcnac_atlas.csv","filename":"rat_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oglcnac_atlas.stat.csv","filename":"rat_protein_xref_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:33.120000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000726/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000726/DRAFT","etag":"7389e1dcdd7210a07c0970e589ca4ad8639aa9acd4c6f209f0d7a3ca5a85103e","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-23T18:20:51.025Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"null","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"null","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-23T18:20:51.025623Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000727/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000727/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d9719b893fefd5dc637489b345da55c7aa291d364ee2eb6288737a9f23fe7f63","provenance_domain":{"name":"Human Protein Biomarkers Citations (Biomarker Database)","version":"v-0.0.0","created":"2023-03-03T02:24:59.574Z","modified":"2024-05-17T11:24:10.870Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Human Protein Biomarkers Citations dataset contains details of the publication present in the dataset Human Protein Cancer Biomarkers https://data.glygen.org/GLY_000625"],"description_domain":{"keywords":["Biomarkers","BiomarkerDB"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"","software_prerequisites":[{"name":"","version":"","uri":{"uri":""}}],"external_data_endpoints":[{"name":"","url":""}]},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_biomarkers.csv","filename":"human_protein_citations_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_biomarkers.stat.csv","filename":"human_protein_citations_biomarkers.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Biomarkers Citations (Biomarker Database)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":168,"last_update":"2024-05-17T11:24:10.870513Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000727/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000727/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"88779d93c1ae2bb9170d5080925ad03b","provenance_domain":{"name":"Human Protein Biomarkers Citations (Biomarker Database)","version":"v-2.1.1","created":"2023-03-03T02:24:59.574Z","modified":"2023-03-03T02:40:02.789Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Human Protein Biomarkers Citations dataset contains details of the publication present in the dataset Human Protein Cancer Biomarkers https://data.glygen.org/GLY_000625"],"description_domain":{"keywords":["Biomarkers","BiomarkerDB"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[{"name":"","url":""}],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_biomarkers.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_biomarkers.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_biomarkers.csv","filename":"human_protein_citations_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_biomarkers.stat.csv","filename":"human_protein_citations_biomarkers.stat.csv"}}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Biomarkers Citations (Biomarker Database)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:23:02.731000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000728/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000728/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"17c2568297ac228d393feb57db44c23d90d6084a38ccc09f5e3d4100d4737a32","provenance_domain":{"name":"Human UniProtKB xref GlyConnect","version":"v-0.0.0","created":"2023-03-03T03:58:28.936Z","modified":"2024-05-17T11:24:10.908Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Human UniProtKB xref GlyConnect dataset contains human(taxid: 9606) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"keywords":["Xref","GlyConnect"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_glyconnect.csv","filename":"human_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_glyconnect.stat.csv","filename":"human_protein_xref_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":128,"last_update":"2024-05-17T11:24:10.908931Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000728/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000728/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0579b4ed8504826d81ac15fefaf39f37","provenance_domain":{"name":"Human UniProtKB xref GlyConnect","version":"v-2.1.1","created":"2023-03-03T03:58:28.936Z","modified":"2023-03-03T03:58:29.019Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Human UniProtKB xref GlyConnect dataset contains human(taxid: 9606) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"keywords":["Xref","GlyConnect"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_glyconnect.csv","filename":"human_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_glyconnect.stat.csv","filename":"human_protein_xref_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:33.451000Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000729/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000729/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"dac10179ee6f444ce026702a2ef905ab88559c37a12fefb930b6f7363103c90e","provenance_domain":{"name":"Mouse UniProtKB xref GlyConnect","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-03T03:58:28.936Z","modified":"2024-12-10T17:30:46.242Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Mouse UniProtKB xref GlyConnect dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_glyconnect.csv","filename":"mouse_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_glyconnect.stat.csv","filename":"mouse_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":168,"last_update":"2024-12-10T17:30:46.242610Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000729/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000729/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fcaa584a5fcb3bf3c38483545f5d4943","provenance_domain":{"name":"Mouse UniProtKB xref GlyConnect","version":"v-2.1.1","created":"2023-03-03T03:58:28.936Z","modified":"2023-03-03T03:58:29.019Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Mouse UniProtKB xref GlyConnect dataset contains mouse(taxid: 10090) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"keywords":["Xref","GlyConnect"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-mus-musculus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_glyconnect.csv","filename":"mouse_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_glyconnect.stat.csv","filename":"mouse_protein_xref_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:33.655000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000730/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000730/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"30dc3af7b6a4532c228d8c46658c153d68dc5bafbb6121ca3009228df7ce902b","provenance_domain":{"name":"Rat UniProtKB xref GlyConnect","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-03T03:58:28.936Z","modified":"2024-12-10T18:47:09.512Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Rat UniProtKB xref GlyConnect dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_glyconnect.csv","filename":"rat_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_protein_xref_glyconnect.stat.csv","filename":"rat_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":171,"last_update":"2024-12-10T18:47:09.512900Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000730/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000730/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d7a44bdf8b01f9d3bda6f7fd6db5c2a5","provenance_domain":{"name":"Rat UniProtKB xref GlyConnect","version":"v-2.1.1","created":"2023-03-03T03:58:28.936Z","modified":"2023-03-03T03:58:29.019Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["Rat UniProtKB xref GlyConnect dataset contains rat(taxid: 10116) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"keywords":["Xref","GlyConnect"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-rattus-norvegicus.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_glyconnect.csv","filename":"rat_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_glyconnect.stat.csv","filename":"rat_protein_xref_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:33.845000Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000731/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000731/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e1011350817f7c29dcc01fd3a71a4ed556a65110ba6f6e193a7242a46380de0c","provenance_domain":{"name":"SARS-CoV2 UniProtKB xref GlyConnect","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-03T03:58:28.936Z","modified":"2024-12-10T19:27:51.833Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["SARS-CoV2 UniProtKB xref GlyConnect dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid: 2697049] UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_glyconnect.csv","filename":"sarscov2_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_glyconnect.stat.csv","filename":"sarscov2_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integsarscov2ion/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":218,"last_update":"2024-12-10T19:27:51.833959Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000731/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000731/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2f5ae4012c633e6d3a57ecf1737f5df6","provenance_domain":{"name":"SARS-CoV2 UniProtKB xref GlyConnect","version":"v-2.1.1","created":"2023-03-03T03:58:28.936Z","modified":"2023-03-03T03:58:29.019Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["SARS-CoV2 UniProtKB xref GlyConnect dataset contains sarscov2 (taxid: 2697049) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"keywords":["Xref","GlyConnect"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sars-cov-2.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_glyconnect.csv","filename":"sarscov2_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_glyconnect.stat.csv","filename":"sarscov2_protein_xref_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:09:04.352000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000732/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000732/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8ec5e6beca94ec5331b940baead97c877088a11b9123d6870eb3796cd6c85b0d","provenance_domain":{"name":"Human Proteoform Glycomics Study Citations (UniCarbKB)","version":"v-0.0.0","created":"2023-03-10T03:38:12.646Z","modified":"2024-05-17T11:24:11.068Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Matthew Campbell","contribution":["contributedBy"],"affiliation":"UniCarbKB","email":"m.campbell2@griffith.edu.au","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains publication information of the PMIDs present in the Human Glycosylation Sites UniCarbKB Glycomics Study dataset (https://data.glygen.org/GLY_000611)."],"description_domain":{"keywords":["Publications","Citations","PubMed","glycomics","UniCarbKB"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB glycosylation sites glycomics study citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":170,"last_update":"2024-05-17T11:24:11.068228Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000732/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000732/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7749806b780afd6c8fa89a35b6dadd9c","provenance_domain":{"name":"Human Proteoform Glycomics Study Citations (UniCarbKB)","version":"v-2.1.1","created":"2023-03-10T03:38:12.646Z","modified":"2023-03-14T17:39:32.376Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Matthew Campbell","contribution":["contributedBy"],"affiliation":"UniCarbKB","email":"m.campbell2@griffith.edu.au","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains publication information of the PMIDs present in the Human Glycosylation Sites UniCarbKB Glycomics Study dataset (https://data.glygen.org/GLY_000611)."],"description_domain":{"keywords":["Publications","Citations","PubMed","glycomics","UniCarbKB"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}],"output_list":[{"filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":""}],"prerequisite":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB glycosylation sites glycomics study citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:23:03.643000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000733/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000733/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"95d5e27380bfe27b99bd50f4b6e2b6cb2d8fbd857c2389f335eac7a06e99d270","provenance_domain":{"name":"Rat Glycosylation Sites UniCarbKB Glycomics Study","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-10T03:58:50.149Z","modified":"2025-03-03T16:13:01.653Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Matthew Campbell","contribution":["contributedBy"],"affiliation":"UniCarbKB","email":"m.campbell2@griffith.edu.au"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat UniCarbKB Glycomics Study contains Rattus norvegicus [taxid: 10116] glycan tissue expression data. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen. UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[]}],"keywords":["Publications","Citations","PubMed","glycomics","UniCarbKB","glycan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB glycosylation sites glycomics study","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":419,"last_update":"2025-03-03T16:13:01.653315Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000733/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000733/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7e1358b4e8f54121f5189b20cc91bf9e","provenance_domain":{"name":"Rat Glycosylation Sites UniCarbKB Glycomics Study","version":"v-2.1.1","created":"2023-03-10T03:58:50.149Z","modified":"2023-03-10T04:12:16.507Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Matthew Campbell","contribution":["contributedBy"],"affiliation":"UniCarbKB","email":"m.campbell2@griffith.edu.au","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":[],"description_domain":{"keywords":["Publications","Citations","PubMed","glycomics","UniCarbKB","glycan"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":"cellline_mapping.csv"},{"uri":"","filename":"n_sequon_info.csv"},{"uri":"","filename":"sample_mapping.csv"},{"uri":"","filename":"tissue_mapping.csv"},{"uri":"","filename":"cellosaurus.txt"},{"uri":"","filename":"known_unicarbkb_glycomics_study.csv"}],"output_list":[{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":""}],"prerequisite":[],"description":""}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"/data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt"}},{"uri":{"filename":"known_unicarbkb_glycomics_study.csv","uri":"/data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB glycosylation sites glycomics study","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:23:03.832000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000734/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000734/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f613af6897dd266569f5e86733ebf2a23a3f7c22e38a41269b902edfa16ad658","provenance_domain":{"name":"Rat Proteoform Glycomics Study Citations (UniCarbKB)","version":"v-0.0.0","created":"2023-03-10T04:00:33.274Z","modified":"2024-05-17T11:24:11.144Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Matthew Campbell","contribution":["contributedBy"],"affiliation":"UniCarbKB","email":"m.campbell2@griffith.edu.au","orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains publication information of the PMIDs present in the Rat Glycosylation Sites UniCarbKB Glycomics Study dataset (https://data.glygen.org/GLY_000733)."],"description_domain":{"keywords":["Publications","Citations","PubMed","glycomics","UniCarbKB"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB glycosylation sites glycomics study citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":168,"last_update":"2024-05-17T11:24:11.144798Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000734/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000734/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"01237cf6a7ec7d533583dedd373c9b21","provenance_domain":{"name":"Rat Proteoform Glycomics Study Citations (UniCarbKB)","version":"v-2.1.1","created":"2023-03-10T04:00:33.274Z","modified":"2023-03-10T04:03:33.194Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Matthew Campbell","contribution":["contributedBy"],"affiliation":"UniCarbKB","email":"m.campbell2@griffith.edu.au","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The dataset contains publication information of the PMIDs present in the Rat Glycosylation Sites UniCarbKB Glycomics Study dataset (https://data.glygen.org/GLY_000733)."],"description_domain":{"keywords":["Publications","Citations","PubMed","glycomics","UniCarbKB"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}],"output_list":[{"filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":""}],"prerequisite":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_unicarbkb_glycomics_study.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB glycosylation sites glycomics study citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T20:23:04.010000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000735/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000735/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8d2d898608d1016344423e161f3e5ea55b7bfd66a5651f44dfd93f8bad2b6343","provenance_domain":{"name":"Fruitfly UniProtKB Xref O-GlcNAcAtlas","version":"v-0.0.0","created":"2023-03-14T18:15:28.807Z","modified":"2024-05-17T11:24:11.181Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref O-GlcNAcAtlas dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to O-GlcNAcAtlas database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAcAtlas and GlyGen. O-GlcNAcAtlas is a a rigorously curated database for experimentally identified O-GlcNAc sites/proteins (https://oglcnac.org/atlas/)"],"description_domain":{"keywords":["Cross-references","Drosophila","O-GlcNAcAtlas"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAcAtlas database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_oglcnac_atlas.csv","filename":"fruitfly_protein_xref_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_xref_oglcnac_atlas.stat.csv","filename":"fruitfly_protein_xref_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":398,"last_update":"2024-05-17T11:24:11.181450Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000735/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000735/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"be7cff95e0613d2e6791136033d2a630","provenance_domain":{"name":"Fruitfly UniProtKB Xref O-GlcNAcAtlas","version":"v-2.1.1","created":"2023-03-14T18:15:28.807Z","modified":"2023-03-14T18:46:17.321Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly UniProtKB Xref O-GlcNAcAtlas dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to O-GlcNAcAtlas database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAcAtlas and GlyGen. O-GlcNAcAtlas is a a rigorously curated database for experimentally identified O-GlcNAc sites/proteins (https://oglcnac.org/atlas/)"],"description_domain":{"keywords":["Cross-references","Drosophila","O-GlcNAcAtlas"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAcAtlas database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oglcnac_atlas.csv","filename":"fruitfly_protein_xref_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oglcnac_atlas.stat.csv","filename":"fruitfly_protein_xref_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:34.574000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000736/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000736/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"aa2e6f019e29737c8c481230f9e53ce446faf5d1eeabc1fbf762b3f1f142bb96","provenance_domain":{"name":"GlyGen-iPTMnet Crossreferences Mapping","version":"v-0.0.0","created":"2023-03-14T19:15:04.425Z","modified":"2024-05-17T11:24:11.219Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The GlyGen-iPTMnet Crossreferences dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], fruitfly [taxid:7227], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of mapping UniProtKB glycosylation site info to PMID and GlyGen glycosylation site view URLs."],"description_domain":{"keywords":["crossreferences","iPTMnet","glycosylation site","UniProtKB"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse, rat, fruitfly, hcv1a, hcv1b, sarscov1 and sarscov2 and extracts it into a csv dataset file."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_iptmnet_xref_mapping.csv","filename":"protein_glygen_iptmnet_xref_mapping.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/protein_glygen_iptmnet_xref_mapping.stat.csv","filename":"protein_glygen_iptmnet_xref_mapping.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-iPTMnet Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":391,"last_update":"2024-05-17T11:24:11.219746Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000736/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000736/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5b1c47f10f9ca83007a0c01b6195958e","provenance_domain":{"name":"GlyGen-iPTMnet Crossreferences Mapping","version":"v-2.1.1","created":"2023-03-14T19:15:04.425Z","modified":"2023-03-14T19:31:14.156Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The GlyGen-iPTMnet Crossreferences dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], fruitfly [taxid:7227], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of mapping UniProtKB glycosylation site info to PMID and GlyGen glycosylation site view URLs."],"description_domain":{"keywords":["crossreferences","iPTMnet","glycosylation site","UniProtKB"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"uri":"","filename":""}],"output_list":[{"uri":"","filename":""}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse, rat, fruitfly, hcv1a, hcv1b, sarscov1 and sarscov2 and extracts it into a csv dataset file."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv"}},{"uri":{"filename":"fruitfly_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"glycan_xref_pubchem.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_xref_pubchem.csv"}},{"uri":{"filename":"hcv1a_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_protein_masterlist.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_protein_masterlist.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_masterlist.csv"}},{"uri":{"filename":"human_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_refseq.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_masterlist.csv"}},{"uri":{"filename":"mouse_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv"}},{"uri":{"filename":"rat_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_refseq.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv"}},{"uri":{"filename":"sarscov1_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_masterlist.csv"}},{"uri":{"filename":"sarscov2_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_refseq.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_iptmnet_xref_mapping.csv","filename":"protein_glygen_iptmnet_xref_mapping.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_glygen_iptmnet_xref_mapping.stat.csv","filename":"protein_glygen_iptmnet_xref_mapping.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-iPTMnet Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:34:22.158000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000737/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000737/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0d4c2fc2df25d988f331be7ff28c54e42f1f0cc8821e38d89222973a0ef7a372","provenance_domain":{"name":"Glycan Biomarkers (Biomarker Database)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-09-03T19:50:12.902Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","contribution":["createdBy","curatedBy"],"affiliation":"The George Washington University","email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Glycan Biomarkers dataset contains glycan biomarker information,  including cross-mapped GlyTouCan accessions, assessed biomarker entity, biomarker type, specimen type, LOINC code, disease name, and source evidence from the biomarker portal (https://data.oncomx.org/allbiomarkers). If you use this dataset, please provide proper attribution to OncoMX and GlyGen. Cite: PMID:32142370, PMID:34015823, and PMID:31616925."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["biomarker","cancer"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_biomarkers.csv","filename":"glycan_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_biomarkers.stat.csv","filename":"glycan_biomarkers.stat.csv"}}]},"execution_domain":{"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Biomarker (BiomarkerDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":510,"last_update":"2026-09-03T19:50:12.902306Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000737/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000737/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"df14fc94d57da71ad13abea80863fd5f","provenance_domain":{"name":"Glycan Biomarkers (Biomarker Database)","version":"v-2.1.1","created":"2023-03-14T20:00:08.127Z","modified":"2023-03-14T20:07:25.567Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","contribution":["createdBy","curatedBy"],"affiliation":"The George Washington University","email":"danlyman@gwu.edu","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Glycan Biomarkers dataset contains glycan biomarker information,  including cross-mapped GlyTouCan accessions, assessed biomarker entity, biomarker type, specimen type, LOINC code, disease name, and source evidence from the biomarker portal (https://data.oncomx.org/allbiomarkers). If you use this dataset, please provide proper attribution to OncoMX and GlyGen. Cite: PMID:32142370, PMID:34015823, and PMID:31616925."],"description_domain":{"keywords":["biomarker","cancer"],"platform":[],"pipeline_steps":[{"name":"","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":""}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/","filename":""}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}},{"uri":{"filename":"doid2uberonid_mapping_v5.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/doid2uberonid_mapping_v5.csv"}},{"uri":{"filename":"allbiomarkers-all.csv","uri":"/data/shared/glyds/downloads/biomarkerdb/2023_04_13/allbiomarkers-all.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_biomarkers.csv","filename":"glycan_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_biomarkers.stat.csv","filename":"glycan_biomarkers.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Biomarker (BiomarkerDB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:34.939000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000738/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000738/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8e11f8ec46b45448fb538c64a85960067f61aa24027fdb513555e8084080c640","provenance_domain":{"name":"Glycan Biomarkers Citations (Biomarker Database)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:13:36.255Z","modified":"2026-09-03T19:51:09.004Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","contribution":["createdBy","curatedBy"],"affiliation":"The George Washington University","email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Glycan Biomarkers Citations dataset contains details of the publications present in the Glycan Biomarkers dataset (https://data.glygen.org/GLY_000737)."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset."}],"keywords":["Publications","Citations","PubMed","Biomarker DB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_biomarkers.csv","filename":"glycan_citations_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_citations_biomarkers.stat.csv","filename":"glycan_citations_biomarkers.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Biomarkers Citations (Biomarker Database)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":191,"last_update":"2026-09-03T19:51:09.004528Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000738/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000738/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b28fca919b8d981d9d9889286cfeee2f","provenance_domain":{"name":"Glycan Biomarkers Citations (Biomarker Database)","version":"v-2.1.1","created":"2023-03-14T20:13:36.255Z","modified":"2023-03-14T20:18:19.753Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","contribution":["createdBy","curatedBy"],"affiliation":"The George Washington University","email":"danlyman@gwu.edu","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Glycan Biomarkers Citations dataset contains details of the publications present in the Glycan Biomarkers dataset (https://data.glygen.org/GLY_000737)."],"description_domain":{"keywords":["Publications","Citations","PubMed","Biomarker DB"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_biomarkers.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_biomarkers.csv"}},{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_biomarkers.csv","filename":"glycan_citations_biomarkers.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/glycan_citations_biomarkers.stat.csv","filename":"glycan_citations_biomarkers.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Biomarkers Citations (Biomarker Database)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepacivirus C"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:35.116000Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000739/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000739/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7efbbc75038ebd0b35f15a18ca2bb312e2cb50b93f06a042093f8415ed227952","provenance_domain":{"name":"Human Germline Mutation Citations","version":"v-0.0.0","created":"2023-03-14T20:20:32.882Z","modified":"2024-05-17T11:24:11.342Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Germline Mutation Citations dataset contains details of the publications present in the Human Germline Mutation dataset (https://data.glygen.org/GLY_000459)."],"description_domain":{"keywords":["Publications","Citations","PubMed","germline mutations","single-nucleotide variations (nsSNVs)","dbSNP","ClinVar","disease"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_mutation_germline.csv","filename":"human_protein_citations_mutation_germline.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_citations_mutation_germline.stat.csv","filename":"human_protein_citations_mutation_germline.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Human Germline Mutation Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":167,"last_update":"2024-05-17T11:24:11.342006Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000739/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000739/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a88bc8552e8a14d4da528fb3575e4e7c","provenance_domain":{"name":"Human Germline Mutation Citations","version":"v-2.1.1","created":"2023-03-14T20:20:32.882Z","modified":"2023-03-14T20:24:42.068Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Human Germline Mutation Citations dataset contains details of the publications present in the Human Germline Mutation dataset (https://data.glygen.org/GLY_000459)."],"description_domain":{"keywords":["Publications","Citations","PubMed","germline mutations","single-nucleotide variations (nsSNVs)","dbSNP","ClinVar","disease"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"","filename":""}],"output_list":[{"filename":"","uri":""}],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[{"uri":{"filename":"human_protein_mutation_germline.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_mutation_germline.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_germline.csv","filename":"human_protein_citations_mutation_germline.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_citations_mutation_germline.stat.csv","filename":"human_protein_citations_mutation_germline.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Human Germline Mutation Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T19:57:35.295000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000740/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000740/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"69d8d8cd1bb0038ace559c6474b1de822a52356e8f819dcb10a2c13f52069c43","provenance_domain":{"name":"Fruitfly Protein Citations (Reactome)","version":"v-0.0.0","created":"2023-03-16T15:25:14.851Z","modified":"2024-05-17T11:24:11.381Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Fruitfly Protein Citations (Reactome) dataset contains details of the publications present in the Fruitfly Protein Reactions (Reactome) dataset (https://data.glygen.org/GLY_000686). "],"description_domain":{"keywords":["Publications","Citations","PubMed","Reactome","Pathway","reactions","PMID"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Fruitfly Protein Citations (Reactome)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":186,"last_update":"2024-05-17T11:24:11.381629Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000741/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000741/DRAFT","spec_version":"","etag":"dae4eaa8bde15672d58d84fbacd8e925c96612b310c883bba6c9f961bf4c35b1","provenance_domain":{"name":"Fruitfly Protein Citations (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T12:49:42.900057","modified":"2024-05-17T11:24:11.422Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.csv","filename":"fruitfly_protein_citations_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/compiled/fruitfly_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_protein_reactions_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_reactome.csv"}},{"uri":{"filename":"fruitfly_protein_xref_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_reactome.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.csv","filename":"fruitfly_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.stat.csv","filename":"fruitfly_protein_citations_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":381,"last_update":"2024-05-17T11:24:11.422164Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000742/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000742/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"86c1173b7b7198cf537b7cdf999c792faa1d1b037dc00da890e5665a5e78e530","provenance_domain":{"name":"Fruitfly Protein Citations (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T12:49:42.900057","modified":"2024-05-17T11:24:11.464Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for Drosophila melanogaster [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_citations_reactome.csv","filename":"fruitfly_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_citations_reactome.stat.csv","filename":"fruitfly_protein_citations_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":342,"last_update":"2024-05-17T11:24:11.464069Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000742/v-2.1.1","contents":{"object_id":"https://biocomputeobject.org/GLY_000742/v-2.1.1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fc0fe806bb2c9eef2e33385577f82e49","provenance_domain":{"name":"Fruitfly Protein Citations (Reactome)","version":"v-2.1.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T12:49:42.900057","modified":"2022-09-26T09:05:27.638299","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"}],"review":[]},"usability_domain":["The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/source/uniprot-proteome-drosophila-melanogaster.nt","filename":"uniprot-proteome-drosophila-melanogaster.nt"},{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_masterlist.csv","filename":"fruitfly_protein_masterlist.csv"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.csv","filename":"fruitfly_protein_citations_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_reactions_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_reactions_reactome.csv"}},{"uri":{"filename":"fruitfly_protein_xref_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_reactome.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.csv","filename":"fruitfly_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_citations_reactome.stat.csv","filename":"fruitfly_protein_citations_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"myglygen66","authorized_users":null,"state":"PUBLISHED","score":0,"last_update":"2023-06-27T18:55:31.973000Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000743/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000743/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"264b2f8b15521e4ce276dc0b162d35b4d348f192568b95f28c35d82df3d04d40","provenance_domain":{"name":"Yeast Protein Isoform sequences (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T12:21:27.326808","modified":"2025-03-04T17:08:41.901Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Isoform sequences (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] protein fasta sequences for the yeast isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all yeast isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","input_list":[]}],"keywords":["protein isoform sequences","fasta","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_allsequences.fasta","filename":"yeast_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_allsequences.stat.csv","filename":"yeast_protein_allsequences.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":349,"last_update":"2025-03-04T17:08:41.901797Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000744/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000744/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"17c59b614ba452f84147c57d41d75fce6e179e1c8c9e7f85c7938c84cec1b4d1","provenance_domain":{"name":"Yeast Protein Alternative Name (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T13:19:31.385999","modified":"2025-03-04T16:48:32.321Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Saccharomyces cerevisiae S288C [taxid:559292] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","input_list":[]}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_altnames.csv","filename":"yeast_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_altnames.stat.csv","filename":"yeast_protein_altnames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":295,"last_update":"2025-03-04T16:48:32.321447Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000745/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000745/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0fdff92879af77e7acad61f66ef2254fcf2e2eb96dc210baece94cb25462fce7","provenance_domain":{"name":"Yeast Protein Binary Interactions (IntAct)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T12:13:07.540218","modified":"2025-03-04T16:53:19.089Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Binary Interaction (IntAct) dataset contains Saccharomyces cerevisiae S288C [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format","input_list":[]}],"keywords":["Binary Interactions","IntAct","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_binary_interactions.csv","filename":"yeast_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_binary_interactions.stat.csv","filename":"yeast_protein_binary_interactions.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":494,"last_update":"2025-03-04T16:53:19.089264Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000746/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000746/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9a1436947d75ca38be233326859e4420fc54ded073267d58cc91aeb2712c35f7","provenance_domain":{"name":"Yeast Protein Canonical sequences (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T14:04:28.411067","modified":"2025-03-04T16:54:50.061Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Canonical (UniProtKB) Sequences dataset contains Saccharomyces cerevisiae S288C [taxid:559292] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all yeast canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","input_list":[]}],"keywords":["protein sequence","fasta","UniProtKB canonical accessions"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_canonicalsequences.fasta","filename":"yeast_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_canonicalsequences.stat.csv","filename":"yeast_protein_canonicalsequences.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":324,"last_update":"2025-03-04T16:54:50.061132Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000747/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000747/DRAFT","etag":"826f09fb8b6e51732ff5e5c31af6e73652514724320232352847bdd88c7feff5","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Citations (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T12:49:42.900057","modified":"2024-05-17T11:24:11.659Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Yeast Protein Reactions (Reactome) dataset contains reactions information for pathways for yeast [taxid:559292] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":377,"last_update":"2024-05-17T11:24:11.659845Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000748/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000748/DRAFT","etag":"058437bb04a045de84d7d6edfc2b48faccddd5864a5752fe0ef575d34fbae8f4","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Citations (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T14:17:09.307325","modified":"2024-05-17T11:24:11.699Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Citations dataset contains publication information for yeast [taxid:559292] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/yeast_protein_blacklisted_pmids_uniprotkb.csv. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","version":"","prerequisite":[],"input_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"uri":"https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/yeast_protein_citations_uniprotkb.csv","filename":"yeast_protein_citations_uniprotkb.csv"}]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"/data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_uniprotkb.csv","filename":"yeast_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_uniprotkb.stat.csv","filename":"yeast_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":527,"last_update":"2024-05-17T11:24:11.699234Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000749/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000749/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f09519a4c1b7a49f5f4ad9a8ca45e8bd6bb353ea3cfce0fe56ad9feb541ee1fb","provenance_domain":{"name":"Yeast Protein Citations (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T14:17:09.307325","modified":"2025-03-04T16:56:07.108Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Citations dataset contains publication information for Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","input_list":[]}],"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_citations_uniprotkb.csv","filename":"yeast_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_citations_uniprotkb.stat.csv","filename":"yeast_protein_citations_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":528,"last_update":"2025-03-04T16:56:07.108822Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000750/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000750/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bfbf81516c13f17dbc46a1e3cb749a4150d5a7a3c560efe272e6468360f25c0a","provenance_domain":{"name":"Yeast Protein Function (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T14:58:43.098400","modified":"2025-03-04T16:59:16.158Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Function (UniProtKB) dataset contains biological function annotation for Saccharomyces cerevisiae S288C [taxid:559292] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["protein function","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_function_uniprotkb.csv","filename":"yeast_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_function_uniprotkb.stat.csv","filename":"yeast_protein_function_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2025-03-04T16:59:16.158172Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000751/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000751/DRAFT","etag":"e1a170ebcf18b59600f205624f58cfdb012116e96285c0687c12f21a4a67a677","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Gene Locus (Ensembl)","version":"v-0.0.0","created":"2020-04-10T11:29:22.824792","modified":"2024-05-17T11:24:11.820Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Gene Locus (Ensembl) contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_genelocus.csv","filename":"yeast_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_genelocus.stat.csv","filename":"yeast_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-17T11:24:11.820126Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000752/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000752/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"342cbb4299c72c3b0346db8b52a321841e0f57f5e8a2dc0f4019f7509aa583cf","provenance_domain":{"name":"Yeast Gene Names (NCBI RefSeq)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T15:40:57.216837","modified":"2025-03-04T16:39:40.808Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Gene Names (NCBI RefSeq) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] gene Names/names (primary gene name and gene synonyms)  from NCBI RefSeq database.  If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the gene Names/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","input_list":[]}],"keywords":["protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_genenames_refseq.csv","filename":"yeast_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_genenames_refseq.stat.csv","filename":"yeast_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":323,"last_update":"2025-03-04T16:39:40.808934Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000753/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000753/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4bc58c656f18f3b89366fcb13653787c817ba7aa50a5767429a5af5fc93fe2d5","provenance_domain":{"name":"Yeast Gene Names (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-04T16:41:16.126Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Gene Names (UniProtKB) dataset contains UniProtKB gene Names/names for Saccharomyces cerevisiae S288C [taxid:559292] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name).  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB gene Names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","input_list":[]}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_genenames_uniprotkb.csv","filename":"yeast_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_genenames_uniprotkb.stat.csv","filename":"yeast_protein_genenames_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":510,"last_update":"2025-03-04T16:41:16.126525Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000754/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000754/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2a8997e1af7efb9a11afe1283ca1ffdcf85eac011f73196208a29b6f0ea8fd39","provenance_domain":{"name":"Yeast Glycohydrolases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T11:23:37.687653","modified":"2025-03-04T16:32:10.014Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycohydrolases dataset contains a list of Saccharomyces cerevisiae S288C [taxid:559292] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","input_list":[]}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_glycohydrolase.csv","filename":"yeast_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_glycohydrolase.stat.csv","filename":"yeast_protein_glycohydrolase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":369,"last_update":"2025-03-04T16:32:10.014957Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000755/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000755/DRAFT","etag":"c179871b068301c5fa75c14f1e0c5102d760ff52190eb14d8c565aea5c07d2ec","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast N-Glycosylation Sequon","version":"v-0.0.0","created":"2022-08-30T16:10:07.494670","modified":"2024-05-17T11:24:11.982Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for yeast [taxid:559292] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_glycosylation_motifs.csv","filename":"yeast_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_glycosylation_motifs.stat.csv","filename":"yeast_protein_glycosylation_motifs.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":333,"last_update":"2024-05-17T11:24:11.982526Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000756/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000756/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b63e75880915d4325474a6fa766241bb1445614da3971aa1b25a258c39a3efd5","provenance_domain":{"name":"Yeast Glycosyltransferases","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T11:20:50.205601","modified":"2025-03-04T16:34:02.798Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycosyltransferases dataset contains a list of Saccharomyces cerevisiae S288C [taxid:559292] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession","input_list":[]}],"keywords":["GT","gycosyltransferase","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_glycosyltransferase.csv","filename":"yeast_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_glycosyltransferase.stat.csv","filename":"yeast_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":381,"last_update":"2025-03-04T16:34:02.798509Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000757/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000757/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4daea336e8a11b5f3f44c1826e5e0ae394fceee2202b91b8a82c57da37b37f35","provenance_domain":{"name":"Yeast Gene Ontology (GO)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T16:13:56.875825","modified":"2025-03-04T16:36:01.741Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Gene Ontology (GO) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. ","input_list":[]}],"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_go_annotation.csv","filename":"yeast_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_go_annotation.stat.csv","filename":"yeast_protein_go_annotation.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":344,"last_update":"2025-03-04T16:36:01.741122Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000758/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000758/DRAFT","etag":"03c117d739e0949f93bfaf444ae839111d9f4f99142eb837659a61b6735066e2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Information (NCBI RefSeq)","version":"v-0.0.0","created":"2022-08-30T16:17:01.573604","modified":"2024-05-17T11:24:12.103Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Information (NCBI RefSeq) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_info_refseq.csv","filename":"yeast_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_info_refseq.stat.csv","filename":"yeast_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":307,"last_update":"2024-05-17T11:24:12.103085Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000759/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000759/DRAFT","etag":"f9842727b451f9d5f75a3464445814e119b395a95e3e10d125d6fd46fc8e7b97","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Information (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T16:19:56.970676","modified":"2024-05-17T11:24:12.139Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Information dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_info_uniprotkb.csv","filename":"yeast_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_info_uniprotkb.stat.csv","filename":"yeast_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-05-17T11:24:12.139968Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000760/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000760/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a1940ba8523b00009b359dd3dd4ff3d8af1c27fd8194d2ff89ec77fa6d93247f","provenance_domain":{"name":"Yeast Proteome Masterlist (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-30T16:22:11.325302","modified":"2025-03-04T18:43:00.967Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Proteome Masterlist dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","input_list":[]}],"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_masterlist.csv","filename":"yeast_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_masterlist.stat.csv","filename":"yeast_protein_masterlist.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":467,"last_update":"2025-03-04T18:43:00.967651Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000761/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000761/DRAFT","etag":"9ef664bcb6a9e8467595a7a5f11dd51b16d76e4cd66e3e80a120dee57f3df495","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast NCBI Protein Linkouts","version":"v-0.0.0","created":"2022-09-14T12:25:39.026264","modified":"2024-05-21T15:53:33.794Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast NCBI Protein Linkouts contains Saccharomyces cerevisiae S288C [taxid:559292] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"step_number":1,"name":"make-species-agnostic-dataset.py","description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_ncbi_linkouts.csv","filename":"yeast_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_ncbi_linkouts.stat.csv","filename":"yeast_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":272,"last_update":"2024-05-21T15:53:33.794994Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000762/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000762/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"75dc093bbf621028230bc337b8cee3ae61ded59a74f744113acf4eebd0aa194f","provenance_domain":{"name":"Yeast EBI-UniProtKB NT file","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T10:27:25.026993","modified":"2025-03-04T16:35:01.227Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast EBI-UniProtKB NT file contains proteome data for Saccharomyces cerevisiae S288C [taxid:559292] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. T If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"description":"The NT file requires no processing after it is received from EMBL-EBI-UniProtKB","input_list":[]}],"keywords":["NT","proteome","EMBL-EBI"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_ntdata.nt","filename":"yeast_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_ntdata.stat.csv","filename":"yeast_protein_ntdata.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":355,"last_update":"2025-03-04T16:35:01.227374Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000763/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000763/DRAFT","etag":"8f38fd1b7d6bba81fbb0c267d8ca0424b2d7fa41675c5d25edb842bceb63e802","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Reaction Participants (Reactome)","version":"v-0.0.0","created":"2022-09-06T11:52:53.037427","modified":"2024-05-21T15:01:13.927Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_participants_reactome.csv","filename":"yeast_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_participants_reactome.stat.csv","filename":"yeast_protein_participants_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":392,"last_update":"2024-05-21T15:01:13.927017Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000764/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000764/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"df8a19db52e7b064fe9f5d8643ef8dfb29503be28b6c68b91070cca6a49d97df","provenance_domain":{"name":"Yeast Reaction Participants (Rhea)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T12:06:00.142793","modified":"2025-03-04T18:44:34.977Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}],"keywords":["Rhea","Participants","Reactions"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_participants_rhea.csv","filename":"yeast_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_participants_rhea.stat.csv","filename":"yeast_protein_participants_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":459,"last_update":"2025-03-04T18:44:34.977808Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000765/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000765/DRAFT","etag":"9289ee0d15b9a3cf8b7523390148667bafbe47b009822a520dd3e17f6fa7f43a","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Pathways (Reactome)","version":"v-0.0.0","created":"2022-09-06T12:11:33.921445","modified":"2024-05-17T11:24:12.373Z","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset contains yeast [taxid:559292] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen","Reactome is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":330,"last_update":"2024-05-17T11:24:12.373391Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000766/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000766/DRAFT","etag":"3d65b501a3a1370f349089b8a21ab438c782ec96c676ec2b4c16bc10e0c5f4fa","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Protein Resource Ontology [Yeast]","version":"v-0.0.0","created":"2022-09-14T12:16:23.572102","modified":"2024-05-21T15:25:52.543Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for Saccharomyces cerevisiae S288C [taxid:559292] proteins. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_pro_annotation.csv","filename":"yeast_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_pro_annotation.stat.csv","filename":"yeast_protein_pro_annotation.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":219,"last_update":"2024-05-21T15:25:52.543516Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000767/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000767/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"525b0f42011bf31981cce13c34bb485ebdbf90f3f8af1584f767e79f1bbab79f","provenance_domain":{"name":"Yeast Protein Names (NCBI RefSeq)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T10:35:44.201343","modified":"2025-03-04T17:09:25.438Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Names (NCBI RefSeq) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","input_list":[]}],"keywords":["protein names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_proteinnames_refseq.csv","filename":"yeast_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_proteinnames_refseq.stat.csv","filename":"yeast_protein_proteinnames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":339,"last_update":"2025-03-04T17:09:25.438272Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000768/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000768/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"be16d671486673240d950fdb7fbc08843f18637dab932bd6aaef793c7638f4ae","provenance_domain":{"name":"Yeast Protein PTM Annotation (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T10:58:38.192589","modified":"2025-03-04T18:35:47.127Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein PTM Annotation (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","input_list":[]}],"keywords":["ptm annotation","glycosylation","phosphorylation"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_ptm_annotation_uniprotkb.csv","filename":"yeast_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_ptm_annotation_uniprotkb.stat.csv","filename":"yeast_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":411,"last_update":"2025-03-04T18:35:47.127987Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000769/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000769/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"d35d1c83b2041ef0b5f8598c0232e010d05f18c1e7ff2108168343f43315603a","provenance_domain":{"name":"Yeast Protein Reactions (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T11:25:28.437609","modified":"2025-03-04T18:38:09.476Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Reactions (Reactome) dataset contains reactions information for pathways for Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","input_list":[]}],"keywords":["Reactome","Pathway","Reactions","PMID"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_reactions_reactome.csv","filename":"yeast_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_reactions_reactome.stat.csv","filename":"yeast_protein_reactions_reactome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":433,"last_update":"2025-03-04T18:38:09.476088Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000770/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000770/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9ef97185ef49acfee2bf779cb03df4f2f1307c14422745b425df4c9781c0341c","provenance_domain":{"name":"Yeast Reactions Rhea","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T11:37:59.766468","modified":"2025-03-04T18:45:41.813Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Reactions (Rhea) dataset contains reactions information for pathways for Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen\""],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","input_list":[]}],"keywords":["Rhea","Reactions","Participants","Enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_reactions_rhea.csv","filename":"yeast_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_reactions_rhea.stat.csv","filename":"yeast_protein_reactions_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":427,"last_update":"2025-03-04T18:45:41.813085Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000771/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000771/DRAFT","etag":"d076cca688fae592f23bdfb7be0dce1cae3210908eb608480ebda06604c2eac1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Recommended Names (UniProtKB)","version":"v-0.0.0","created":"2022-08-31T11:01:36.870249","modified":"2024-05-21T14:03:56.424Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Saccharomyces cerevisiae S288C [taxid:559292] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","input_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_recnames.csv","filename":"yeast_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_recnames.stat.csv","filename":"yeast_protein_recnames.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":243,"last_update":"2024-05-21T14:03:56.424102Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000772/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000772/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e1017dc36ad88cb61845951bc19594749a9023e6f7c1e889af3f912720495092","provenance_domain":{"name":"Yeast Protein Sequence Info (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T11:03:51.938138","modified":"2025-03-04T18:39:48.319Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Sequence Info (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB sequence for all yeast isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format","input_list":[]}],"keywords":["protein sequence info","fasta header","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_sequenceinfo.csv","filename":"yeast_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_sequenceinfo.stat.csv","filename":"yeast_protein_sequenceinfo.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":354,"last_update":"2025-03-04T18:39:48.319050Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000773/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000773/DRAFT","etag":"f12265f62afa9d347e0b8787bc12ace2defa4cef264cffa4d83613fd049d9a54","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Signal Peptide","version":"v-0.0.0","created":"2022-08-31T11:05:56.022652","modified":"2024-06-03T22:37:18.184Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Signal Peptide dataset contains Saccharomyces cerevisiae S288C [taxid:559292] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. Signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. ","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_annotation.csv","filename":"yeast_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_peptidesequences.fasta","filename":"yeast_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_cleavedsequences.fasta","filename":"yeast_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_fullsequences.fasta","filename":"yeast_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_annotation.stat.csv","filename":"yeast_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_peptidesequences.stat.csv","filename":"yeast_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_cleavedsequences.stat.csv","filename":"yeast_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_signalp_fullsequences.stat.csv","filename":"yeast_protein_signalp_fullsequences.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":703,"last_update":"2024-06-03T22:37:18.184749Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000774/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000774/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"e79c5dd79ffb6dfe2e697ce2144e40340e0dba592b49bf901bb8f201b0c8a09b","provenance_domain":{"name":"Yeast Protein Site Annotation","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T11:08:19.037259","modified":"2025-03-04T18:41:16.899Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Site Annotation (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range.  If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","input_list":[]}],"keywords":["site annotation","amino acid range","UniProtKB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_site_annotation_uniprotkb.csv","filename":"yeast_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_site_annotation_uniprotkb.stat.csv","filename":"yeast_protein_site_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":402,"last_update":"2025-03-04T18:41:16.899849Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000775/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000775/DRAFT","etag":"1d6ee47df1f0c9cfe2ef12e9d408111fed9df4ae136d4cb7ac10f138736dc5b6","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Submitted Names (UniProtKB)","version":"v-0.0.0","created":"2022-08-31T11:11:10.067141","modified":"2024-05-17T11:24:12.763Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for yeast [taxid:559292] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_submittednames.csv","filename":"yeast_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_submittednames.stat.csv","filename":"yeast_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":502,"last_update":"2024-05-17T11:24:12.763113Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000776/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000776/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"91c93a9c55461adceee5a9efde4a98d8af3f82edc5982223c285beed307ca941","provenance_domain":{"name":"Yeast Transcript Locus (Ensembl Transcript coordinates)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T11:17:02.109861","modified":"2025-11-04T12:33:00.770Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Transcript Locus (Ensembl Transcript coordinates) contains UniProtKB Saccharomyces cerevisiae [taxid:559292] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Ensembl and GlyGen. "],"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are mapped to ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file, and then maps any UniProtKB isoforms to the UniProtKB canonical accession. The transcript ID is then used to extract the transcript's chromosome, start position, end position and forward/reverse strand data from the Ensembl gene annotation GTF file which has been converted to a TSV file. The extracted data is then used to create the csv dataset. ","input_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_transcriptlocus.csv","filename":"yeast_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_transcriptlocus.stat.csv","filename":"yeast_protein_transcriptlocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":495,"last_update":"2025-11-04T12:33:00.770138Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000777/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000777/DRAFT","etag":"79654085decc34b8e73794c340dd5d2578a9f6c3c846633393002719dd13701e","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast UniProtKB Xref Reactome","version":"v-0.0.0","created":"","modified":"2024-05-17T11:24:12.840Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast UniProtKB Xref Reactome dataset contains yeast [taxid:559292] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene expression","Reactome","cross-reference"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Reactome database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2024-05-17T11:24:12.840482Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000778/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000778/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"396d0ed0f6b6f81b8074bbe53515b070f0a59f9351cdbee1bef16e695c812c30","provenance_domain":{"name":"Yeast UniProtKB Xref BRENDA","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T12:42:59.923930","modified":"2025-03-04T18:49:03.258Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniprotKB Xref BRENDA contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","input_list":[]}],"keywords":["enzyme","ec number","BRENDA","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_brenda.csv","filename":"yeast_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_brenda.stat.csv","filename":"yeast_protein_xref_brenda.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":601,"last_update":"2025-03-04T18:49:03.258782Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000779/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000779/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"30048cdbe8af66c3ffa86406c3298d6928b7ca690f9683c7a36b2fd4cd2f7a3b","provenance_domain":{"name":"Yeast UniProtKB Xref CAZy","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T12:46:03.864774","modified":"2025-03-04T18:57:32.658Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniprotKB Xref CAZy contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","input_list":[]}],"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_cazy.csv","filename":"yeast_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_cazy.stat.csv","filename":"yeast_protein_xref_cazy.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":588,"last_update":"2025-03-04T18:57:32.658822Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000780/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000780/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3fef01e115427c01d84241c93d09e5e3449db953d1f8ca16ae10d7e23b1fc25b","provenance_domain":{"name":"Yeast UniProtKB Xref CDD","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T12:47:56.887721","modified":"2025-03-04T18:59:26.459Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref CDD contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","input_list":[]}],"keywords":["protein domains","CDD","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_cdd.csv","filename":"yeast_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_cdd.stat.csv","filename":"yeast_protein_xref_cdd.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":535,"last_update":"2025-03-04T18:59:26.459797Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000781/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000781/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b9d639dd8c5881118c8b4498d7b76d864c8ae4d6b8c39528a8f4429b955c0492","provenance_domain":{"name":"Yeast UniProtKB Xref ChEMBL","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:04:19.896737","modified":"2025-03-04T19:01:54.204Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniprotKB Xref ChEMBL contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","input_list":[]}],"keywords":["bioactivity","ChEMBL","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_chembl.csv","filename":"yeast_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_chembl.stat.csv","filename":"yeast_protein_xref_chembl.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":458,"last_update":"2025-03-04T19:01:54.204391Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000782/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000782/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f1a77346959389d3f078f50b199263a340e256cd943734fd701266e86e78afd9","provenance_domain":{"name":"Yeast UniProtKB Xref SGD","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-01T11:43:42.773513","modified":"2024-12-10T22:14:44.623Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref The Saccharomyces Genome Database (SGD) contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to The Saccharomyces Genome Database (SGD) database accessions/identifiers.  If you use this dataset please provide proper attribution to The Saccharomyces Genome Database (SGD) and GlyGen.","The Saccharomyces Genome Database (SGD) provides comprehensive integrated biological information for the budding yeast Saccharomyces cerevisiae."],"description_domain":{"keywords":["The Saccharomyces Genome Database (SGD)","cross-reference","yeast"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to SDG database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_sgd.csv","filename":"yeast_protein_xref_sgd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_sgd.stat.csv","filename":"yeast_protein_xref_sgd.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"The Saccharomyces Genome Database (SGD) cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":606,"last_update":"2024-12-10T22:14:44.623372Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000783/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000783/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"50dc12f6e6bf90aa833905533c9d86adf5c765533facbe8da3346213a5c4d606","provenance_domain":{"name":"Yeast UniProtKB Xref NCBI Gene","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:07:41.419400","modified":"2025-03-04T19:11:42.817Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref NCBI Gene dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.   If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["gene id","NCBI gene","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_geneid.csv","filename":"yeast_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_geneid.stat.csv","filename":"yeast_protein_xref_geneid.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":636,"last_update":"2025-03-04T19:11:42.817226Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000784/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000784/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"15a627156273f9c13eaa80f5da29184640d7042669485b0f8dcdb53940629c19","provenance_domain":{"name":"Yeast UniProtKB Xref IntAct","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:13:10.878546","modified":"2025-03-04T19:03:51.077Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref IntAct dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_intact.csv","filename":"yeast_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_intact.stat.csv","filename":"yeast_protein_xref_intact.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":665,"last_update":"2025-03-04T19:03:51.077137Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000785/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000785/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a23c4fd84d4d7b99fc90018082241016712ac00825e23ba26d765756f619adb2","provenance_domain":{"name":"Yeast UniProtKB Xref InterPro","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:16:01.810293","modified":"2025-03-04T19:07:02.249Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref InterPro contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_interpro.csv","filename":"yeast_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_interpro.stat.csv","filename":"yeast_protein_xref_interpro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":585,"last_update":"2025-03-04T19:07:02.249917Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000786/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000786/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6323dfa60b9827f9f60cf9d1d6806c2f0c93edd29e2e24d393225780ddecddd7","provenance_domain":{"name":"Yeast UniProtKB Xref KEGG PATHWAY","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:17:32.978920","modified":"2025-03-04T19:09:02.061Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref KEGG PATHWAY contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["pathways","reactions","KEGG Pathway","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_kegg.csv","filename":"yeast_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_kegg.stat.csv","filename":"yeast_protein_xref_kegg.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":519,"last_update":"2025-03-04T19:09:02.061144Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000787/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000787/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bf71f992ca84fdff5a5def7f4ed3d3758c2191fea2ab7330c411b6d1b99522d3","provenance_domain":{"name":"Yeast UniProtKB Xref O-GlcNAcAtlas","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T18:15:28.807Z","modified":"2025-03-04T20:57:55.056Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref O-GlcNAcAtlas dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to O-GlcNAcAtlas database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAcAtlas and GlyGen. O-GlcNAcAtlas is a a rigorously curated database for experimentally identified O-GlcNAc sites/proteins (https://oglcnac.org/atlas/)"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAcAtlas database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["Cross-references","Drosophila","O-GlcNAcAtlas"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_oglcnac_atlas.csv","filename":"yeast_protein_xref_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_oglcnac_atlas.stat.csv","filename":"yeast_protein_xref_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2025-03-04T20:57:55.056954Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000788/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000788/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9d3203c8ee094ededf14e3151e558be825fc69ef2a40761478fe2a367165da73","provenance_domain":{"name":"Yeast UniProtKB Xref O-GlcNAc (MCW)","version":"v-0.0.0","license":"httpss://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:46:26.989814","modified":"2025-03-04T19:12:59.207Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref O-GlcNAc (MCW) contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O - GlcNAc(MCW) is a database for O - GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["Drosophila","O-GlcNAc (MCW)","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_oglcnac_mcw.csv","filename":"yeast_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_oglcnac_mcw.stat.csv","filename":"yeast_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":464,"last_update":"2025-03-04T19:12:59.207784Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000789/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000789/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6882df029fc85f42c44f107e0686a1d8fe747731080dcdf58a4b4fd098668991","provenance_domain":{"name":"Yeast UniProtKB Xref OMA","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:20:12.938783","modified":"2025-03-04T20:59:10.797Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref OMA contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["orthologs","OMA","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_oma.csv","filename":"yeast_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_oma.stat.csv","filename":"yeast_protein_xref_oma.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":459,"last_update":"2025-03-04T20:59:10.797296Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000790/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000790/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4ba5c15c100d5adcff3b96cdc3940da8d2fbb705a6b97afdac918c9995148cc1","provenance_domain":{"name":"Yeast UniProtKB Xref OrthoDB","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:25:53.921490","modified":"2025-03-04T21:00:14.693Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref OrthoDB contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["orthologs","OrthoDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_orthodb.csv","filename":"yeast_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_orthodb.stat.csv","filename":"yeast_protein_xref_orthodb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":539,"last_update":"2025-03-04T21:00:14.693432Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000791/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000791/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"37f461cfd94eefaeb020546a379d542a49401648df941209fe5e2c092a04a09d","provenance_domain":{"name":"Yeast UniProtKB Xref PANTHER","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:34:27.210052","modified":"2025-03-04T21:01:46.576Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref PANTHER contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["protein family","PANTHER","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_panther.csv","filename":"yeast_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_panther.stat.csv","filename":"yeast_protein_xref_panther.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":585,"last_update":"2025-03-04T21:01:46.576778Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000792/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000792/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4184e4039a3888e16eff4b545d56000ed66ec854a647a9c38777b3e91d874dbf","provenance_domain":{"name":"Yeast UniProtKB Xref PDB","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:40:29.038163","modified":"2025-03-04T21:03:27.342Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref PDB contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["protein 3D structure","RCSB PDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_pdb.csv","filename":"yeast_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_pdb.stat.csv","filename":"yeast_protein_xref_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":495,"last_update":"2025-03-04T21:03:27.342595Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000793/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000793/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"da9c8e6a27f1937a7017f791d820211915a97ac13cd392e18381ed9f2db4c5b8","provenance_domain":{"name":"Yeast UniProtKB Xref Pfam","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:42:50.669379","modified":"2025-03-04T21:04:45.822Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref Pfam contains Saccharomyces cerevisiae S288C [TaxID: 559292] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["protein family","Pfam","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_pfam.csv","filename":"yeast_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_pfam.stat.csv","filename":"yeast_protein_xref_pfam.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":495,"last_update":"2025-03-04T21:04:45.822007Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000794/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000794/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"8ed6e05a1ea492180a0d524f9a7e3cf460be03414d6ff9b44584287565ab1baf","provenance_domain":{"name":"Yeast UniProtKB Xref PRO","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-31T13:44:37.770122","modified":"2024-12-10T19:02:55.888Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniprotKB Xref PRO contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["protein ontology","PRO","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_pro.csv","filename":"yeast_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_pro.stat.csv","filename":"yeast_protein_xref_pro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":493,"last_update":"2024-12-10T19:02:55.888121Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000795/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000795/DRAFT","etag":"89fb4578643e7b9c2437ea2f48a355e7a6acf227022e3bb2407e2b71e7e0a97e","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:13.548Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":[],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:13.548895Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000796/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000796/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b189d4103fff88e33a60f5f3d34a19e92d25a252690bfa16eeabeb191a8b42a8","provenance_domain":{"name":"Yeast UniProtKB Xref RefSeq","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-14T12:24:23.479851","modified":"2024-12-10T19:01:28.630Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniprotKB Xref RefSeq contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["protein accessions","RefSeq","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_refseq.csv","filename":"yeast_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_refseq.stat.csv","filename":"yeast_protein_xref_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":792,"last_update":"2024-12-10T19:01:28.630366Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000797/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000797/DRAFT","etag":"3d641d670e35af15a4137ecdf58855d079d82f36e7d22e9be3d8f62f029dd361","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:13.629Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":[],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:13.629907Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000798/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000798/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast UniProtKB Xref (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T16:55:15.307877","modified":"2024-05-21T14:41:08.181Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_uniprotkb.csv","filename":"yeast_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_uniprotkb.stat.csv","filename":"yeast_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{},"etag":"6cc8f8a1659b5d65e10f7947b0dfc45625976e71d62021e309209d52ea527c18"},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":274,"last_update":"2024-05-21T14:41:08.181955Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000799/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000799/DRAFT","etag":"4cdebc35138f6e3de59225fc9bd16e25b569a0c37276a3a467c731665f6f40b0","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Proteoform Citations (GlyConnect)","version":"v-0.0.0","created":"2022-09-02T10:28:05.203794","modified":"2024-05-17T11:24:13.717Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file httpss://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (httpss://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"yeast_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"yeast_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":442,"last_update":"2024-05-17T11:24:13.717886Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000800/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000800/DRAFT","etag":"1ff525daebe0f119754edd462f7a74894614146b1554b7df0fbd5f543d3d8fe7","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-0.0.0","created":"2023-02-27T21:08:01.227Z","modified":"2024-05-17T11:24:13.758Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu ","orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Yeast O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000711, contributed by Jungfeng Ma's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"yeast_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"yeast_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":251,"last_update":"2024-05-17T11:24:13.758933Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000801/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000801/DRAFT","etag":"20131ccf79311bd1bf827a6e17e4a5c1211bc238ddf4b74e705fc31f57a9dfb7","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-0.0.0","created":"2022-09-02T10:30:49.524483","modified":"2024-05-17T11:24:13.797Z","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Yeast O-GlcNAc Glycosylation Sites (MCW)  httpss://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed","MCW","Glycosylation"],"platform":[],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"yeast_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"yeast_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"param":"","value":"","step":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":236,"last_update":"2024-05-17T11:24:13.797324Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000802/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000802/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Proteoform Glycosylation Citations (UniProtKB)","version":"v-0.0.0","created":"2022-09-02T10:55:15.390409","modified":"2024-05-17T11:24:13.833Z","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"httpss://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Proteoform Glycosylation Citations (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] citation details of the publications present in the dataset Yeast Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000808)."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Glycosylation"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","input_list":[]}]},"execution_domain":{"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"yeast_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"yeast_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"etag":"85695a167972a260c80b39fc59349dca55ad90191515564f4b471c64305c40d0"},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":255,"last_update":"2024-05-17T11:24:13.833859Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000803/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000803/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6562184d859f9f496ab40206ff692f5b74c9eddb727b82143d3ee01a2344bfd3","provenance_domain":{"name":"Yeast Proteoform Phosphorylation Citations (iPTMnet)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-02T13:26:18.780372","modified":"2024-12-05T19:40:07.397Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Proteoform Citations (iPTMNet) contains Saccharomyces cerevisiae [taxid:559292] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","input_list":[]}],"keywords":["PMID","journal","citations","authors","iPTMnet","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"yeast_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"yeast_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":434,"last_update":"2024-12-05T19:40:07.397517Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000804/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000804/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"f4020eff61663db5109a2f85be4b361fd4fa6a1a6b998333c1375f412f7a1e01","provenance_domain":{"name":"Yeast Proteoform Phosphorylation Citations (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-02T13:32:35.505543","modified":"2025-10-09T14:37:59.595Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Proteoform Phosphorylation Citations (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] publication information of phosphorylated glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","input_list":[]}],"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"yeast_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"yeast_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":386,"last_update":"2025-10-09T14:37:59.595971Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000805/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000805/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"0ba7b5384dc1e3c823f095d25d7fd5ffdcd1748e4fc1f5e8bd82b347e5030e22","provenance_domain":{"name":"Yeast Glycosylation Sites (GlyConnect) ","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T12:24:13.810189","modified":"2025-03-04T16:08:05.568Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycosylation Sites (GlyConnect) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions with information on reported glycans in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Saccharomyces cerevisiae (strain ATCC 204508 / S288c)). If you use this dataset please provide proper attribution to GlyConnect and GlyGen. Please note that this dataset contains only glycan data and does not include protein or site information."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the latest UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (yeast_proteoform_glycosylation_sites_glyconnect.1.log) In this dataset the script only extracts the glycan information. CURRENTLY - THE ABOVE QC STEP IS NOT DONE AS THE DATA DOES NOT HAVE PROTEIN AND SITES.","input_list":[]}],"keywords":["glycosylation","reported glycosylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_glyconnect.csv","filename":"yeast_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"yeast_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":816,"last_update":"2025-03-04T16:08:05.568350Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000806/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000806/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b127182918a80cc87619da6c52c489344d5a5b9e146c80f75250f48f64126f76","provenance_domain":{"name":"Yeast O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2025-03-04T16:36:52.414Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu "},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Saccharomyces cerevisiae S288C [TaxID: 559292] O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":[null,"O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"yeast_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":369,"last_update":"2025-03-04T16:36:52.414111Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000807/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000807/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3f70ef83d793f02a43d960235712a9b4320f04b65018a3bad8af1f6715a102a2","provenance_domain":{"name":"Yeast O-GlcNAc Glycosylation Sites (MCW)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:56:25.251283","modified":"2025-03-04T16:50:33.173Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast O-GlcNAc Glycosylation Sites (MCW) contains Saccharomyces cerevisiae S288C [taxid:559292] O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Yeast O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s yeast protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to yeast species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding yeast UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"yeast_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":2987,"last_update":"2025-03-04T16:50:33.173851Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000808/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000808/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"70f1d2e8e25012ccf189c316e466a81d1157e4c558c572e711bcace7c4d7f9c6","provenance_domain":{"name":"Yeast Glycosylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T09:50:57.220135","modified":"2025-03-04T16:33:00.524Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycosylation Sites (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","input_list":[]}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_uniprotkb.csv","filename":"yeast_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"yeast_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288c","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":379,"last_update":"2025-03-04T16:33:00.524594Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000809/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000809/DRAFT","etag":"60603846637f89e961e0858d25fbfa6d26ebbbca23db6a3ed90d567345004bc6","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Phosphorylation Sites (iPTMNet)","version":"v-0.0.0","created":"2022-09-06T09:56:04.354720","modified":"2024-05-21T14:47:58.363Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Phosphorylation Sites (iPTMNet) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["iPTMnet","Phosphorylation sites"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","description":"The script extracts the phosphorylation information from the source dataset as per taxid and extracts as a csv dataset. The protein accession and sites are mapped to the UniProtKB canonical accession and fasta sequence.","version":"1","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_phosphorylation_sites_iptmnet.csv","filename":"yeast_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"yeast_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-05-21T14:47:58.363454Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000810/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000810/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6cbf22f528f136c727555a8205c408e76db9be775624a0249a2d034a75213f37","provenance_domain":{"name":"Yeast Phosphorylation Sites (UniProtKB)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-09-06T09:53:09.953304","modified":"2025-03-04T16:38:50.025Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Phosphorylation Sites (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","input_list":[]}],"keywords":["phosphoryation Sites","ptm processing","UniProtKB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"yeast_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"yeast_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":399,"last_update":"2025-03-04T16:38:50.025475Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000811/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000811/DRAFT","etag":"4896cf31928df3d91f911a8bc322781f780a2dabf3719a34b406e474ba7f7174","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Yeast Protein Enzyme Annotation (UniProtKB)","version":"v-0.0.0","created":"2022-08-30T14:44:26.008676","modified":"2024-06-03T20:44:46.061Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Protein Enzyme Annotation (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_enzyme_annotation_uniprotkb.csv","filename":"yeast_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"yeast_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2024-06-03T20:44:46.061090Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000812/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000812/DRAFT","etag":"6d7033daa2de7d9d967e36a4a991d7abeabffe01a4a8a958a7c2e5d7efbd1640","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Fruitlfly UniProtKB xref GlyConnect","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.215Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Fruitlfly UniProtKB xref GlyConnect dataset contains fruitlfly(taxid: 559292) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Xref","GlyConnect"],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integfruitlflyion/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_glyconnect.csv","filename":"yeast_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_glyconnect.stat.csv","filename":"yeast_protein_xref_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":138,"last_update":"2024-05-17T11:24:14.215891Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000813/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000813/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2a3ff107174926c4f9b991cb29d3d8a02ab96dc8b32c71f2b8d67e8641b20d2d","provenance_domain":{"name":"Fruitfly UniProtKB xref GlyConnect","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-03T03:58:28.936Z","modified":"2026-03-23T20:11:51.959Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Fruitfly UniProtKB xref GlyConnect dataset contains fruitfly(taxid: 7227) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_glyconnect.csv","filename":"fruitfly_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_glyconnect.stat.csv","filename":"fruitfly_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integfruitflyion/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":165,"last_update":"2026-03-23T20:11:51.959466Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000814/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000814/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"2973edd734f60c3e63302ed6425f076c40e8ec9dd76cef76c35a847e48bd2773","provenance_domain":{"name":"Common Fund Data Ecosystem (CFDE) Data Package","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-12-15T20:24:01.916Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Common Fund Data Ecosystem (CFDE) Data Package contains submitted datasets containing GlyGen metadata to the CFDE portal as a zip package for a given release. The datasets are created as per the CFDE's direction using a custom script and files - https://github.com/glygener/glygen.cfde.generator"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[]}],"keywords":["CFDE","Data Package"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/all_cfde_data_package.zip","filename":"all_cfde_data_package.zip"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/all_cfde_data_package.stat.csv","filename":"all_cfde_data_package.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepatitis c virus (isolate h)"},{"category_name":"species","category_value":"Hepatitis c virus (isolate japanese)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)"},{"category_name":"molecule"},{"category_value":"Common Fund Data Ecosystem (CFDE) Data Package","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2025-12-15T20:24:01.916147Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000815/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000815/DRAFT","etag":"b577905f49877713ffbeb6144c202303f44f7fcdbb02dad578569ccd3cf0ef21","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"EuropePMC Linkouts","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.330Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The EuropePMC Linkouts contains XML files that contains NCBI PubMed IDs associated with all of GlyGen's proteins and glycans with their corresponding GlyGen publication detail page URLs. Glycan Image URL is also present if available. The dataset is formatted as per EuropePMC linkouts guidelines where 2167 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into multiple XML files of <10MB and packaged as a zip file. For more info - https://gwu0.sharepoint.com/:w:/r/sites/GlyGenTeam-GRP/Shared%20Documents/Backend/Documents/EuropePMC%20linkouts.docx?d=w8fc9c465fd094eee89b370747e7eac80&csf=1&web=1&e=ZiatbN and https://europepmc.org/LabsLink"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Hepatitis c virus (isolate h)"},{"category_name":"species","category_value":"Hepatitis c virus (isolate japanese)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae (strain ATCC 204508 / S288c)"},{"category_value":"","category_name":"molecule"},{"category_value":"EuropePMC Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["EuropePMC Linkouts","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the PubMed IDs from the input files associated with proteins and glycans in GlyGen and generates publication detail page URLs for corresponding proteins and glycans; glycan URLs for glycans when available. The script also enters the other fields as defined by the EuropePMC Linkouts to generate a csv dataset that is split into multiple XML files of <10MB and packaged as a zip file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"zip","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_one.zip","filename":"all_europepmc_linkouts_one.zip"}},{"mediatype":"zip","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_two.zip","filename":"all_europepmc_linkouts_two.zip"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_one.stat.csv","filename":"all_europepmc_linkouts_one.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_two.stat.csv","filename":"all_europepmc_linkouts_two.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":693,"last_update":"2024-05-17T11:24:14.330507Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000816/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000816/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"734af09cb05447cdda6eed59c1a65d14036c948cea82f25125145c6eb52677fb","provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref ViralGlycome","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T19:26:15.185Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) UniProtKB Xref ViralGlycome contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to ViralGlycome database - https://viral.glycomics.ku.dk.","The ViralGlycome creates visualization of CCG-generated viral O-glycoproteomics datasets and put them in the context of other types of glycosylation, evolutionary conservation, and immune reactivity."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ViralGlycome database accessions/identifiers and extracts the data as a csv dataset"}],"keywords":["ViralGlycome","viral glycosylation viewer","cross-reference","viral O-glycoproteomics datasets"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_viralglycome.csv","filename":"sarscov2_protein_xref_viralglycome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/sarscov2_protein_xref_viralglycome.stat.csv","filename":"sarscov2_protein_xref_viralglycome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViralGlycome cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":547,"last_update":"2024-12-10T19:26:15.185648Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000817/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000817/DRAFT","etag":"7a2551f0412f1f41543d9b5dceaadca04a46a12fe09deec3001675689b8c54a9","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Glycan Sequences GlycoCTXML","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.407Z","derived_from":[],"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Nathan Edwards","affiliation":"Georgetown University","email":"nje5@georgetown.edu","contribution":["contributedBy"],"orcid":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@gwu.edu","contribution":[],"orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The dataset provides the glycan sequences in GlycoCT{XML} format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Sequences were generated by Nathan Edwards. Source database: https://glytoucan.org/"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCTXML sequence format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H)"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"},{"category_name":"species","category_value":"Sus scrofa domesticus"}]}}],"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"filename":"glycan_masterlist.csv","access_time":"","uri":"","sha1_checksum":""},{"filename":"names.tsv","access_time":"","uri":"","sha1_checksum":""},{"filename":"subsumption.tsv","access_time":"","uri":"","sha1_checksum":""},{"filename":"glycoctxml.zip.00","access_time":"","uri":"","sha1_checksum":""},{"filename":"glycoctxml.zip.01","access_time":"","uri":"","sha1_checksum":""},{"filename":"glycoctxml.zip.02","access_time":"","uri":"","sha1_checksum":""},{"filename":"glycoctxml.zip.03","access_time":"","uri":"","sha1_checksum":""}],"output_list":[],"prerequisite":[],"description":"The input files were downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the glycan master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"filename":"glycan_sequences_glycoctxml.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_glycoctxml.csv","access_time":"","sha1_checksum":""}},{"mediatype":"csv","uri":{"filename":"glycan_sequences_glycoctxml.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/glycan_sequences_glycoctxml.stat.csv","access_time":"","sha1_checksum":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":321,"last_update":"2024-05-17T11:24:14.407142Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000818/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000818/DRAFT","etag":"171ec636fcaf99b03c4d3379dd80f8a8155a9035d3086c463071d4e2bc4ca2e9","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Rat Protein Citations (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.448Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Protein Reactions (Reactome) dataset contains reactions information for pathways for rat [taxid:10116] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":372,"last_update":"2024-05-17T11:24:14.448295Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000819/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000819/DRAFT","etag":"94b4c561045a976d718b89200de5245408eb22a8fce374c715267c92c8249036","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Mouse Protein Citations (Reactome)","version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.486Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Protein Reactions (Reactome) dataset contains reactions information for pathways for mouse [taxid:10090] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":376,"last_update":"2024-05-17T11:24:14.486986Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000820/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000820/DRAFT","etag":"835ba473afc2d993a64eedd6ec1292c387af04c9edc166b447da953988f66821","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"version":"v-0.0.0","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-23T18:21:30.635Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"null","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"null","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}]},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-23T18:21:30.635672Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000821/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000821/DRAFT","etag":"1c98102b4bf522622e003c1a5092c1d9bc4d299af2ebcc7518ed0046a49d485b","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Glycan SNFG images (JSON format)","version":"2.3","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.561Z","derived_from":[],"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Nathan Edwards","affiliation":"Georgetown University","email":"nje5@georgetown.edu","contribution":["contributedBy"],"orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The dataset provides supporting JSON files for glymagesvg semantic highlighting for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan (https://glytoucan.org/) accession master list (https://data.glygen.org/GLY_000281). Source files are retrieved from https://github.com/glygen-glycan-data/PyGly/"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"tar","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","json"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"filename":"images-snfg-extended-json.tbz.00","access_time":"","uri":"https://data.glygen.org/ln2data/downloads/glytoucan/current/export/images-snfg-extended-json.tbz.00","sha1_checksum":""}],"output_list":[{"filename":"images-snfg-extended-json.tbz","access_time":"","uri":"https://data.glygen.org/ln2data/downloads/glytoucan/current/export/images-snfg-extended-json.tbz","sha1_checksum":""}],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands: 1. cat images-snfg-extended-json.tbz.?? > images-snfg-extended-json.tbz 2. tar xvf images-snfg-extended-json.tbz \nThe folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycan_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/glycan_masterlist.csv"}}],"output_subdomain":[{"mediatype":"tar","uri":{"uri":"https://data.glygen.org/ln2releases/data/v-2.3.1/reviewed/glycan_images_snfg_extended_json.tar.gz","filename":"glycan_images_snfg_extended_json.tar.gz"}},{"mediatype":"csv","uri":{"uri":"https://data.glygen.org/ln2releases/data/v-2.3.1/reviewed/glycan_images_snfg_extended_json.tar.stat.csv","filename":"glycan_images_snfg_extended_json.tar.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":353,"last_update":"2024-05-17T11:24:14.561743Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000822/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000822/DRAFT","etag":"a95bcc9d30654a521bd658942751522cdf8896e86553cab37f17502e423bf44f","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dictyostelium Glycosylation Sites (GlyConnect)","version":"2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.598Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","email":"frederique.lisacek@sib.swiss","contribution":["contributedBy"],"orcid":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dictyostelium Glycosylation Sites (GlyConnect) dataset contains dictyostelium [taxid:44689] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/glycosylations?taxonomy=Dictyostelium%20discoideum)."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen dictyostelium protein masterlist and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the UniProtKB release for that protein (however it does pass if the amino acid +glyco-site is empty, as these records correspond to the \\\"not reported\\\" glyco-sites) and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist (https://data.glygen.org/GLY_000281)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"","filename":""}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"uri":"https://data.glygen.org/ln2data/downloads/glyconnect/current/glyconnect_dicty.json","filename":"glyconnect_dicty.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https://data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_glycosylation_sites_glyconnect.csv","filename":"dicty_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https://data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"dicty_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":382,"last_update":"2024-05-17T11:24:14.598939Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000823/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000823/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"570672f8222906a3d2a4bfe517bad46982f05752d1b322cb0a6d9cdc9bc1e39b","provenance_domain":{"name":"Dictyostelium Phosphorylation Sites (UniProtKB)","version":"2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:22:36.335Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","email":"martin@ebi.ac.uk","contribution":["contributedBy"]},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","email":"pvasudev@ebi.ac.uk","contribution":["contributedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Phosphorylation Sites (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from the UniProtKB Dictyostelium discoideum proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset."}],"keywords":["phosphoryation sites","ptm processing","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"uri":"https://data.glygen.org/ln2data/downloads/ebi/current/uniprot-proteome-dictyostelium-discoideum.nt","filename":"/data/shared/glyds/downloads/ebi/2023_10_30/uniprot-proteome-dictyostelium-discoideum.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https://data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"dicty_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https://data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"dicty_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":384,"last_update":"2024-12-10T17:22:36.335115Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000824/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000824/DRAFT","etag":"15c5bab81da9c92f84561fb0136c5a737f8c7605a37fd72192ec4b81ef232cda","spec_version":"1.3.0","provenance_domain":{"name":"Dictyostelium Glycation Sites (UniProtKB)","version":"RETIRED","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.675Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dictyostelium Glycation Sites (UniProtKB) dataset contains dictyostelium [taxid:44689] UniProtKB canonical accessions with information on glycation sites with evidence in UniProtKB database. The dataset is derived from the UniProtKB Dictyostelium discoideum proteome release."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycation sites","UniProtKB"],"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script loads the glycation information from the triplestore conatining triples from the nt file and extracts as a csv dataset.","version":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"filename":"dicty_proteoform_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"filename":"dicty_proteoform_glycation_sites_uniprotkb.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":279,"last_update":"2024-05-17T11:24:14.675087Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000825/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000825/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Dictyostelium Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:14.714Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dictyostelium Proteoform Glycosylation Citations (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] citation details of the publications present in the dataset Dictyostelium Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000827)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"dicty_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"dicty_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"dicty_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{},"etag":"6396613686ae486b44e673ecb77a8b868ebbeb462dc9030516f9dfe4b054a7d8"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":264,"last_update":"2024-05-17T11:24:14.714562Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000826/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000826/DRAFT","spec_version":"1.3.0","etag":"c8cc613f56cdd6007246ac35eef05e1989b2f3a97734584f2802aa162f41da3a","provenance_domain":{"name":"Dictyostelium Proteoform Phosphorylation Citations (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:23:46.568Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Proteoform Phosphorylation Citations (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"dicty_proteoform_phosphorylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_phosphorylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"dicty_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"dicty_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2024-12-10T17:23:46.568112Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000827/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000827/DRAFT","spec_version":"1.3.0","etag":"c2bb65f90b30ecde9a4b135cd69d95cef8f11dee2cb95691df3f9f6e814f8939","provenance_domain":{"name":"Dictyostelium Glycosylation Sites (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:21:42.983Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Glycosylation Sites (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Dictyostelium discoideum proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2023_10_11/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-dictyostelium-discoideum.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-dictyostelium-discoideum.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.csv","filename":"dicty_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"dicty_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2024-12-10T17:21:42.983415Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000828/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000828/DRAFT","etag":"cc8ec81bb7451441c1fd95d8e80956051c75cf41df94cbf7e202f448bc7de880","spec_version":"1.3.0","provenance_domain":{"name":"Dictyostelium Proteoform Glycation Citations (UniProtKB)","version":"RETIRED","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.823Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["Dictyostelium Proteoform Glycation Citations (UniProtKB) dataset contains dictyostelium [taxid:44689] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"filename":"dicty_proteoform_citations_glycation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"filename":"dicty_proteoform_citations_glycation_sites_uniprotkb.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_citations_glycation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":283,"last_update":"2024-05-17T11:24:14.823423Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000829/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000829/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"360b598949737e9912729bac37241da6819b88feb8e5bee928c78f3d54053cc2","provenance_domain":{"name":"Dicty Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-04T15:54:04.901Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["\"The Dicty Protein Isoform sequences (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] protein fasta sequences for the dicty isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all dicty isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}],"keywords":["protein isoform sequences","fasta","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_allsequences.fasta","filename":"dicty_protein_allsequences.fasta"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":343,"last_update":"2025-03-04T15:54:04.901605Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000830/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000830/DRAFT","etag":"8c03b89381b2f5c4060ee5300680c19b45426cd31bb36930d36558834ef6546c","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Alternative Name (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.896Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Dictyostelium discoideum [taxid:44689] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/dicty_protein_altnames.csv","filename":"dicty_protein_altnames.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":236,"last_update":"2024-05-17T11:24:14.896059Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000831/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000831/DRAFT","etag":"6e961e72173aeb4f37747acf6dbb67b323772ad594b814c8c24941c52ac93e08","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Binary Interactions (IntAct)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:14.935Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Binary Interaction (IntAct) dataset contains Dictyostelium discoideum [taxid:44689] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_binary_interactions.csv","filename":"dicty_protein_binary_interactions.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":403,"last_update":"2024-05-17T11:24:14.935613Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000832/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000832/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"b48549583ff3bb02e3c408df5996d4746a46241e52934cec05d8d3ad533f6c85","provenance_domain":{"name":"Dicty Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-03-04T15:48:44","modified":"2025-03-04T15:51:22.203Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein Canonical (UniProtKB) Sequences dataset contains Dictyostelium discoideum [taxid:44689] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the UniProtKB fasta sequence for all dicty canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}],"keywords":["protein sequence","fasta","UniProtKB canonical accessions"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"dicty_protein_canonicalsequences.fasta","filename":"dicty_protein_canonicalsequences.fasta"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":317,"last_update":"2025-03-04T15:51:22.203264Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000833/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000833/DRAFT","etag":"995ea965e08ca25e0bbd0ae62ce9423edbfcb7e3b5b9dccf99498fc051e380ad","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Citations (Reactome)","version":"RETIRED","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.013Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Reactions (Reactome) dataset contains reactions information for pathways for dicty [taxid:44689] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","version":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"filename":"dicty_protein_citations_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"filename":"dicty_protein_citations_reactome.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":376,"last_update":"2024-05-17T11:24:15.013877Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000834/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000834/DRAFT","etag":"cbcd36256f4f11de05b0abac0a4be773951afcb3ca35f4660673e1c328bea536","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Citations (RefSeq)","version":"RETIRED","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.051Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Citations (RefSeq) datasets contains dicty [taxid:44689] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"filename":"dicty_protein_citations_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"filename":"dicty_protein_citations_refseq.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":377,"last_update":"2024-05-17T11:24:15.051540Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000835/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000835/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Citations (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:15.090Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein Citations dataset contains publication information for Dictyostelium discoideum [taxid:44689] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_citations_uniprotkb.csv","filename":"dicty_protein_citations_uniprotkb.csv"}}]},"etag":"70bc9e905a44b9e3cd4ba4bd375a6c4ab2453e4c6f5e5ab0a440a9fb372573df"},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":429,"last_update":"2024-05-17T11:24:15.090305Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000836/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000836/DRAFT","etag":"a334f706a16dc2087483f30682c3f1aa758173d6bbef0c7b9095d991d23a99cb","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Enzyme Annotation (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T20:45:16.886Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein Enzyme Annotation (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Enzyme Annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["enzyme annotation","enzyme","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_enzyme_annotation_uniprotkb.csv","filename":"dicty_protein_enzyme_annotation_uniprotkb.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":330,"last_update":"2024-06-03T20:45:16.886331Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000837/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000837/DRAFT","etag":"729ba1f743504162bba764e43addf265d8967be4384c1e550008414f73ed3d47","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Function (NCBI Refseq)","version":"RETIRED","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.167Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Function (NCBI RefSeq) dataset contains biological function annotation of dicty [taxid:44689] genes from GeneRIF section in the NCBI RefSeq database. The dataset is downloaded from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"filename":"dicty_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"filename":"dicty_protein_function_refseq.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":325,"last_update":"2024-05-17T11:24:15.167448Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000838/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000838/DRAFT","etag":"600b747179b47c97b1db86a5a14481ee94abc18e39edc430f7de58888eea5e50","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Function (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.207Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Function (UniProtKB) dataset contains biological function annotation for Dictyostelium discoideum [taxid:44689] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_function_uniprotkb.csv","filename":"dicty_protein_function_uniprotkb.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":269,"last_update":"2024-05-17T11:24:15.207096Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000839/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000839/DRAFT","etag":"5b62e12e0deaf60193197fea748c7d84b1bb2ed254a5617ea978718a3b111c68","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Gene Symbols (NCBI RefSeq)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.243Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Gene Symbols (NCBI RefSeq) dataset contains Dictyostelium discoideum [taxid:44689] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_genenames_refseq.csv","filename":"dicty_protein_genenames_refseq.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":261,"last_update":"2024-05-17T11:24:15.243219Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000840/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000840/DRAFT","etag":"e19c68b8ddb2c6ce7a8991d257f9d5a46065da70b24e2471e3cca7ab139a6307","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Gene Symbols (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.280Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Dictyostelium discoideum [taxid:44689] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.\n    ],"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_genenames_uniprotkb.csv","filename":"dicty_protein_genenames_uniprotkb.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":423,"last_update":"2024-05-17T11:24:15.280206Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000841/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000841/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"7f86fdb19fce864ce4c6c141fa9c6a3a7da47549e9acf57b685531e66a7b2229","provenance_domain":{"name":"Dicty Glycohydrolases","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:16:40.821Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Glycohydrolases dataset contains a list of Dictyostelium discoideum [taxid:44689] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_glycohydrolase.csv","filename":"dicty_protein_glycohydrolase.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":365,"last_update":"2024-12-10T17:16:40.821161Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000842/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000842/DRAFT","etag":"d567e75f82a5d6dd44eb721f1427ab4e28021359b544e99068b8cce1cf54d586","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty N-Glycosylation Sequon","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T20:45:36.719Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Dictyostelium discoideum [taxid:44689] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_glycosylation_motifs.csv","filename":"dicty_protein_glycosylation_motifs.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":350,"last_update":"2024-06-03T20:45:36.719413Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000843/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000843/DRAFT","etag":"92d97e54966257bde57d983181e4806519a4fcb4b909382dfbd64be2eef651b4","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Glycosyltransferases","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.397Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Glycosyltransferases dataset contains list of dicty [taxid:44689] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the dicty proteome was retrieved with the following search terms: keyword:\\\"Complete proteome [KW-0181]\\\" (now removed from UniProtKB) AND reviewed:yes AND organism:\\\"Dictyostelium discoideum (Dicty) [44689]\\\". To retrieve the list of all dicty glycosyltransferases, the full list of dicty proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_glycosyltransferase.csv","filename":"dicty_protein_glycosyltransferase.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":2002,"last_update":"2024-05-17T11:24:15.397351Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000844/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000844/DRAFT","etag":"73955228112e3f395e0815beebaa9375214350852d3efe0be1267f28783e76cd","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Gene Ontology (GO)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.437Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Gene Ontology (GO) dataset contains Dictyostelium discoideum [taxid:44689] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_go_annotation.csv","filename":"dicty_protein_go_annotation.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":275,"last_update":"2024-05-17T11:24:15.437471Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000845/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000845/DRAFT","etag":"5e897a3562ddb716c3041ab86ffde2c96c6a7698a1083aadde7f6f7c9daf49a6","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Information (NCBI RefSeq)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.476Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Information (NCBI RefSeq) dataset contains Dictyostelium discoideum [taxid:44689] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_info_refseq.csv","filename":"dicty_protein_info_refseq.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":300,"last_update":"2024-05-17T11:24:15.476969Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000846/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000846/DRAFT","etag":"931c64647bb1e004c7343df8a3da94c10042bcd929f70c54e89c6e66db22b24f","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Information (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.517Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Information dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_info_uniprotkb.csv","filename":"dicty_protein_info_uniprotkb.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":294,"last_update":"2024-05-17T11:24:15.517079Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000847/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000847/DRAFT","etag":"7ec60e6b8479ec2032c72502a7d491f4b86342af110698b55dc20c4a2781ea03","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Proteome Masterlist (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T20:30:37.402Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Proteome Masterlist dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_masterlist.csv","filename":"dicty_protein_masterlist.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":305,"last_update":"2024-06-03T20:30:37.402733Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000848/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000848/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"17005ba80b0ef129c3ed868680dc1fbb715fb614bfe88207a8d746c593d0eaab","provenance_domain":{"name":"Dicty EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-04T15:44:45.828Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty EBI-UniProtKB NT file contains proteome data for Dictyostelium discoideum [taxid:44689] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}],"keywords":["NT","proteome","EMBL-EBI"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"dicty_protein_ntdata.nt","filename":"dicty_protein_ntdata.nt"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":345,"last_update":"2025-03-04T15:44:45.828264Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000849/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000849/DRAFT","etag":"c33e878f39009a473e996ee41071085e570eb291e968b594382cd270dd6c0e69","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Reaction Participants (Reactome)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T15:07:42.056Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Dictyostelium discoideum [taxid:44689] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[null]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/dicty_protein_participants_reactome.csv","filename":"dicty_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/dicty_protein_participants_reactome.stat.csv","filename":"dicty_protein_participants_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":385,"last_update":"2024-05-21T15:07:42.056171Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000850/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000850/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"9799e8479f4c1f5affa05805e0c65df6998397d4c835c2175ca487dc2b93c3d0","provenance_domain":{"name":"Dicty Reaction Participants (Rhea)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-06T15:22:42.037Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Reaction Participants (Rhea) dataset offers detailed information on enzymatic participants involved in chemical and transport reactions specific to Dictyostelium discoideum [TaxID: 44689]. Rhea is a rigorously curated knowledgebase that catalogs biologically significant reactions and serves as the authoritative standard for enzyme and transporter annotation in UniProtKB. To characterize reaction participants, Rhea leverages the Chemical Entities of Biological Interest (ChEBI) dictionary."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[null]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_participants_rhea.csv","filename":"dicty_protein_participants_rhea.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":607,"last_update":"2025-03-06T15:22:42.037982Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000851/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000851/DRAFT","etag":"2955a5e324eeae57156003ccdfdd4f67c9be65744dea3a69428077602fc8f41b","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Pathways (Reactome)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T15:42:16.411Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Pathways (Reactome) dataset contains Dictyostelium discoideum [taxid:44689] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_pathways_reactome.csv","filename":"dicty_protein_pathways_reactome.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":372,"last_update":"2024-05-21T15:42:16.411261Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000852/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000852/DRAFT","etag":"b6ef7928f4034ff71209a19493279b4862903bbe092af2b0c6bcb86ba61990ea","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Names (NCBI RefSeq)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.752Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Names (NCBI RefSeq) dataset contains Dictyostelium discoideum [taxid:44689] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_proteinnames_refseq.csv","filename":"dicty_protein_proteinnames_refseq.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":272,"last_update":"2024-05-17T11:24:15.752204Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000853/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000853/DRAFT","etag":"d4ee62dcfd264139db71812283b267357e6ab3f93149dc5c42c0487eb37c9275","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein PTM Annotation (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:01:40.798Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein PTM Annotation (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_ptm_annotation_uniprotkb.csv","filename":"dicty_protein_ptm_annotation_uniprotkb.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":323,"last_update":"2024-06-03T21:01:40.798350Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000854/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000854/DRAFT","etag":"742078a9c05eb18a554fcd5bce8ca646296f7147543b4d287b86f0e66f9eb601","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Citations (Reactome)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.826Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Reactions (Reactome) dataset contains reactions information for pathways for dicty [taxid:44689] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["Reactome","Pathway","Reactions"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"","uri":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"","filename":""}},{"mediatype":"csv","uri":{"uri":"","filename":""}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":376,"last_update":"2024-05-17T11:24:15.826516Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000855/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000855/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"3664751c1215263f861fa496c97d8e4072005dd4f6f4f47c685f5c50f59fd752","provenance_domain":{"name":"Dicty Reactions (Rhea)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-06T15:28:09.574Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Reaction (Rhea) dataset offers detailed information on enzymatic pathways and equations involved in chemical and transport reactions specific to Dictyostelium discoideum [TaxID: 44689]. Rhea is a rigorously curated knowledgebase that catalogs biologically significant reactions and serves as the authoritative standard for enzyme and transporter annotation in UniProtKB. To characterize reaction participants, Rhea leverages the Chemical Entities of Biological Interest (ChEBI) dictionary. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[null]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_reactions_rhea.csv","filename":"dicty_protein_reactions_rhea.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":605,"last_update":"2025-03-06T15:28:09.574486Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000856/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000856/DRAFT","etag":"902badbb0e8c3b12d01bde1e8b8cf3f1603da4d6bb8b268a284b8431d56e33d3","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Recommended Names (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:08:53.710Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Dictyostelium discoideum [taxid:44689] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_recnames.csv","filename":"dicty_protein_recnames.csv"}},{"mediatype":"csv","uri":{"filename":"dicty_protein_recnames.stat.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_recnames.stat.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":237,"last_update":"2024-05-21T14:08:53.710495Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000857/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000857/DRAFT","etag":"5f6c409d89b13d2e70a789091419cef9201be647b249d9ba69e5081668e1c56c","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Sequence Info (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.940Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Sequence Info (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all dicty isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_sequenceinfo.csv","filename":"dicty_protein_sequenceinfo.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":285,"last_update":"2024-05-17T11:24:15.940651Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000858/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000858/DRAFT","etag":"c367515e0e5ef25e54f2a6825b8f76d2d193fc6989d47efcedcab5f52f4eda73","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Signal Peptide","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:15.978Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Signal Peptide dataset contains Dictyostelium discoideum [taxid:44689] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_signalp_annotation.csv","filename":"dicty_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"filename":"dicty_protein_signalp_cleavedsequences.fasta","uri":"dicty_protein_signalp_cleavedsequences.fasta.fasta","access_time":"2024-01-10T05:00:00.000Z"}},{"mediatype":"fasta","uri":{"filename":"dicty_protein_signalp_fullsequences.fasta","uri":"dicty_protein_signalp_fullsequences.fasta","access_time":"2024-01-10T05:00:00.000Z"}},{"mediatype":"fasta","uri":{"filename":"dicty_protein_signalp_peptidesequences.fasta","uri":"dicty_protein_signalp_peptidesequences.fasta","access_time":"2024-01-10T05:00:00.000Z"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":695,"last_update":"2024-05-17T11:24:15.978891Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000859/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000859/DRAFT","etag":"dcd4c03e9f5e3d634f14032998a8189c2d50b590363996bb32fccd5ff3af2db9","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Site Annotation","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:02:04.548Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein Site Annotation (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_site_annotation_uniprotkb.csv","filename":"dicty_protein_site_annotation_uniprotkb.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":324,"last_update":"2024-06-03T21:02:04.548182Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000860/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000860/DRAFT","etag":"02574cbc3b01f3e52e3f395c117404ab72bc2795be00f2f76a893eaacdb407cc","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Submitted Names (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.058Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Dictyostelium discoideum [taxid:44689] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_submittednames.csv","filename":"dicty_protein_submittednames.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":521,"last_update":"2024-05-17T11:24:16.058470Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000861/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000861/DRAFT","etag":"ddeed17ff0f6ab99a4cceb7abc617481ebbf491126b56d561fd89b3df6f69a7c","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref Bgee","version":"RETIRED","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.096Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref Bgee dataset contains dicty [taxid:44689] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. \",\n        \"Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_bgee.csv","filename":"dicty_protein_xref_bgee.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":531,"last_update":"2024-05-17T11:24:16.096512Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000862/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000862/DRAFT","etag":"ec1e1f82a72d12070267055b36cec56c51245340fe8da57a65c3cd9d17cbbcd3","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref BRENDA","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.132Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniprotKB Xref BRENDA contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.\n        BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_brenda.csv","filename":"dicty_protein_xref_brenda.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":499,"last_update":"2024-05-17T11:24:16.132590Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000863/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000863/DRAFT","etag":"3427951657214d72cd610123d57625114c677773398519c04528a33032f80b6a","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref CAZy","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.170Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniprotKB Xref CAZy contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.\n        CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_cazy.csv","filename":"dicty_protein_xref_cazy.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":488,"last_update":"2024-05-17T11:24:16.170497Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000864/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000864/DRAFT","etag":"36032ceb880a196e43be6a3819b70b6fe2a8c491eadac9381c4a1ec1ccdb0d1b","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref CDD","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.210Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref CDD contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.\n        \"The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"CDD cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_cdd.csv","filename":"dicty_protein_xref_cdd.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":443,"last_update":"2024-05-17T11:24:16.210211Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000865/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000865/DRAFT","etag":"c7e89e4485f8f51cf44872fd8827105838d53875031e58cbd2319ef48e2ed1eb","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref ChEMBL","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.247Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniprotKB Xref ChEMBL contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.\n        ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ChEMBL cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_chembl.csv","filename":"dicty_protein_xref_chembl.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":379,"last_update":"2024-05-17T11:24:16.247523Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000866/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000866/DRAFT","etag":"d0603fa0b7f21fb820ea8682189690f1e1bd142af767ff158c170149b206abfd","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-23T18:21:59.204Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"null","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"null","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[null]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv"},{"mediatype":"csv"}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-23T18:21:59.204697Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000867/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000867/DRAFT","etag":"0f9c22fe06941e484aa6a728dbe04d222e9120a2139ba406a351b0bf5a7f95c1","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref NCBI Gene","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.322Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref NCBI Gene dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.\n        NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_geneid.csv","filename":"dicty_protein_xref_geneid.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":527,"last_update":"2024-05-17T11:24:16.322192Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000868/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000868/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"4ae87ebca42b7f2cbc228ff241290c89388abdd9af1cc3e62dc78d1d6c3165d4","provenance_domain":{"name":"Dicty UniProtKB xref GlyConnect","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:20:15.877Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Dicty UniProtKB xref GlyConnect dataset contains Dictyostelium discoideum [taxid: 44689] UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_glyconnect.csv","filename":"dicty_protein_xref_glyconnect.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":183,"last_update":"2024-12-10T17:20:15.877021Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000869/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000869/DRAFT","etag":"f1d17f5e7b6364d70ae808d82af9aaa56f0fa18fbfec0878136cb56a403e1e95","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref IntAct","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.396Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref IntAct dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.\n        IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_intact.csv","filename":"dicty_protein_xref_intact.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":549,"last_update":"2024-05-17T11:24:16.396993Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000870/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000870/DRAFT","etag":"e4e1636632f2adcb317ad91478f39b7875f133a851119648bac622ce0a616de7","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref InterPro","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.435Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref InterPro contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_interpro.csv","filename":"dicty_protein_xref_interpro.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":477,"last_update":"2024-05-17T11:24:16.435589Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000871/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000871/DRAFT","etag":"0dc62ae05138d35b10c6e53492e8ef1d5a8dfafca5505e9d924a7243f8820b53","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref KEGG PATHWAY","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:02:28.165Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty UniProtKB Xref KEGG PATHWAY contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"KEGG Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_kegg.csv","filename":"dicty_protein_xref_kegg.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":422,"last_update":"2024-06-03T21:02:28.165765Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000872/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000872/DRAFT","etag":"40e00799e35800bd1683fc70e021cbc6e438ed1f0a19c6daec88428d558d3a0e","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref OMA","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.510Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref OMA contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"OMA cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_oma.csv","filename":"dicty_protein_xref_oma.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":372,"last_update":"2024-05-17T11:24:16.510200Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000873/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000873/DRAFT","etag":"37d784f6a785254379bc4d20daffc3cf92b7dd73e5e117da6f50d32562a8ce82","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref PANTHER","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.545Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref PANTHER contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PANTHER cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_panther.csv","filename":"dicty_protein_xref_panther.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":477,"last_update":"2024-05-17T11:24:16.545534Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000874/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000874/DRAFT","etag":"c24a5c60ae46c32f51f988f2cad41870bdce3bcde91123137626434a6aa4564f","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref PDB","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:02:45.854Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty UniProtKB Xref PDB contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_pdb.csv","filename":"dicty_protein_xref_pdb.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":400,"last_update":"2024-06-03T21:02:45.854768Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000875/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000875/DRAFT","etag":"754f07dd220e923f252bfbcd2044ff3d096ff854073a631e53c6a699630ebb15","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref Pfam","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.620Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref Pfam contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_pfam.csv","filename":"dicty_protein_xref_pfam.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":399,"last_update":"2024-05-17T11:24:16.620899Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000876/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000876/DRAFT","etag":"5ce14df872eeae9203d89ae96279bcd82df826770d174fc03fe1c3ab31df59ac","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref PRO","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.660Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniprotKB Xref PRO contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRO cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_pro.csv","filename":"dicty_protein_xref_pro.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":398,"last_update":"2024-05-17T11:24:16.660539Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000877/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000877/DRAFT","etag":"bdd1ee66edda7fdd363874b0bb6ceb1262369afa081a0115e16225288252b920","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref Reactome","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:02:57.815Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty UniProtKB Xref Reactome contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_reactome.csv","filename":"dicty_protein_xref_reactome.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":359,"last_update":"2024-06-03T21:02:57.815626Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000878/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000878/DRAFT","etag":"77fd555dd5a82f145a8dda13b8f921269a582010d865ef8c88afb54fbe247bec","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty Protein Xref NCBI RefSeq","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.737Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref NCBI RefSeq contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to NCBI RefSeq database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI Reference Sequence (RefSeq) collection provides a comprehensive, integrated, non-redundant, well-annotated set of sequences, including genomic DNA, transcripts, and proteins."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI RefSeq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_refseq.csv","filename":"dicty_protein_xref_refseq.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":451,"last_update":"2024-05-17T11:24:16.737187Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000879/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000879/DRAFT","etag":"1f414f3e2c54bca5e68927d42a0101c24d66cbaa0f098f53b6a3b5faf7de345b","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref Rhea","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.774Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref Rhea contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"RHEA cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_rhea.csv","filename":"dicty_protein_xref_rhea.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":259,"last_update":"2024-05-17T11:24:16.774044Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000880/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000880/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref (UniProtKB)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:36:22.768Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty UniProtKB Xref (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["UniProtKB","cross-references"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_uniprotkb.csv","filename":"dicty_protein_xref_uniprotkb.csv"}}]},"etag":"0cdb31b3d3ca59957dce739a5e2567030796785181608cf15e64961b5ddb02b9"},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":267,"last_update":"2024-05-21T14:36:22.768241Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000881/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000881/DRAFT","etag":"0f4894492748e02200211e87b236a281ac22da72572705362190cf3cd9d096d2","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Dicty UniProtKB Xref dictyBase","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.848Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Dicty UniProtKB Xref dictyBase contains dicty [taxid:44689] UniProtKB canonical accessions cross-referenced to the dictyBase database accessions/identifiers.  If you use this dataset please provide proper attribution to the dictyBase Database and GlyGen\ndictyBase (http://dictybase.org) is the model organism database (MOD) for the social amoeba Dictyostelium discoideum."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Dictyostelium discoideum","dictyBase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to dictyBase database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_xref_dictybase.csv","filename":"dicty_protein_xref_dictybase.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":375,"last_update":"2024-05-17T11:24:16.848652Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000882/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000882/DRAFT","etag":"87f73b46f2030dc668d5f843dc9b113d9995c55e3c60a682e0a86944625f2414","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Fruitfly Protein Diseases","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:16.889Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Fruitfly Protein Diseases contains diseases associated with the fruitfly [taxid:7227] protein UniProtKB canonical accessions. The dataset also contains mapping of UniProtKB canonical accessions to the Disease Ontology (DO), Mondo and OMIM resources.\nIf you use this dataset please provide proper attribution to GlyGen and Alliance of Genome Resources."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["disease","fruitfly","mim","do","mondo"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"fruitfly_protein_disease_alliance_genome.csv","filename":"fruitfly_protein_disease_alliance_genome.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":355,"last_update":"2024-05-17T11:24:16.889488Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000883/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000883/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"1bae351b64dab8f36adb826a480891ae84b754c4456115b1370c46997afc5673","provenance_domain":{"name":"Yeast Protein Diseases","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-03-04T16:57:23","modified":"2025-03-04T16:57:59.271Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Protein Diseases contains diseases associated with the Saccharomyces cerevisiae S288C [taxid:559292] protein UniProtKB canonical accessions. The dataset also contains mapping of UniProtKB canonical accessions to the Disease Ontology (DO), Mondo and OMIM resources. If you use this dataset please provide proper attribution to GlyGen and Alliance of Genome Resources."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[]}],"keywords":["disease","yeast","mim","do","mondo"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"yeast_protein_disease_alliance_genome.csv","filename":"yeast_protein_disease_alliance_genome.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":456,"last_update":"2025-03-04T16:57:59.271865Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000884/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000884/DRAFT","etag":"763ddd0876ec4d7132b27e15df815ed2429536ad9f391850ed676d61f54cb410","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"SARS-CoV2 Gene Locus (Ensembl)","version":"RETIRED","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:03:20.728Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV2 Gene Locus (Ensembl) contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["gene coordinates","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"sarscov2_protein_genelocus.csv","filename":"sarscov2_protein_genelocus.csv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":353,"last_update":"2024-06-03T21:03:20.728797Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000885/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000885/DRAFT","etag":"43d4437bc9ff4ba65efaebef7dc53779ad5fb139c32bc1cbc9bbedc1ecd5115c","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"GlyGen-MGI Crossreferences Mapping","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.003Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The GlyGen-MGI Crossreferences Mapping dataset contains mouse [taxid:10090] UniProtKB accessions mapped to Mouse Genome Informatics (MGI) IDs. The dataset also contains glycosylation annotation information for the given UniProtKB accession and the corresponding URL for the GlyGen Protein Detail Page."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-MGI Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["MGI","cross-references","GlyGen"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for mouse, maps it to the MGI IDs, extracts glycosylation annotation and creates a URL for the entry all into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"protein_glygen_mgi_xref_mapping.tsv","filename":"protein_glygen_mgi_xref_mapping.tsv"}}]}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-05-17T11:24:17.003371Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000886/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000886/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"06f506598b975fc41a9cbb1f172d48a10c500cd0f4010abc1815080707a96b73","provenance_domain":{"name":"Dicty Protein Reactions (Reactome)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:18:44.483Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Protein Reactions (Reactome) dataset contains reactions information for pathways for Dictyostelium discoideum [taxid:44689] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}],"keywords":["Reactome","Pathway","Reactions","PMID"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"dicty_protein_reactions_reactome.csv","filename":"dicty_protein_reactions_reactome.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":413,"last_update":"2024-12-10T17:18:44.483850Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000887/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000887/DRAFT","spec_version":"1.3.0","etag":"d73877c1680b2952c5a5addf63750445fa18da5c144e42bb839438406aab27f6","provenance_domain":{"name":"Dicty Proteoform Citations (GlyConnect)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-01-29T20:20:36","modified":"2024-12-05T19:24:46.152Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID). The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}],"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"dicty_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"dicty_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"dicty_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jeetvora96","authorized_users":null,"state":"DRAFT","score":477,"last_update":"2024-12-05T19:24:46.152478Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000888/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000888/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Human Glycosylation Sites (EMBL)","version":"1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T13:23:51.724Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Clement Potel","affiliation":"EMBL","email":"clement.potel@embl.de","contribution":["contributedBy"]},{"name":"Mira Burtscher","affiliation":"EMBL","email":"mira.burtscher@embl.de","contribution":["contributedBy"]},{"name":"Martin Garrido","affiliation":"EMBL","email":"martin.garrido@embl.de","contribution":["contributedBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites (EMBL) dataset contains glycosylation information (mainly for N-glycosylation) on Homo sapiens (taxid:9606) cell line (HelaK and HEK293T) proteins. The data is submitted by Dr. Clement Potel, Dr. Mira Burtscher and Dr. Martin Garrido, of the Genome Biology Unit, EMBL based on the publication 'Deep quantitative glycoproteomics reveals gut microbiome induced remodeling of the brain glycoproteome.' GlyTouCan accessions were mapped by the GlyGen team to the glycan compositions provided by the authors. If you use this dataset please provide proper attribution to the data source [1], EMBL and GlyGen.","References: 1) Potel C, Burtscher ML, Garrido-Rodriguez M, Brauer-Nikonow A, Becher I, Typas A, Zimmermann M, Savitski M. Deep quantitative glycoproteomics reveals gut microbiome induced remodeling of the brain glycoproteome. bioRxiv 2023.09.13.557529; doi:10.1101/2023.09.13.557529."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[null]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"filename":"human_proteoform_glycosylation_sites_embl.csv","uri":"https://data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_embl.csv"}},{"mediatype":"csv","uri":{"filename":"human_proteoform_glycosylation_sites_embl.stat.csv","uri":"https://data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_embl.stat.csv"}}]},"etag":"8e4bf6d57e5d03987f8ac02fa849793b91c56de7e5492b7287e2c44ba4792e08"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":914,"last_update":"2024-05-21T13:23:51.724538Z","access_count":12},{"object_id":"https://biocomputeobject.org/GLY_000889/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000889/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Mouse Glycosylation Sites (EMBL)","version":"1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T13:20:32.008Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Clement Potel","affiliation":"EMBL","email":"clement.potel@embl.de","contribution":["contributedBy"]},{"name":"Mira Burtscher","affiliation":"EMBL","email":"mira.burtscher@embl.de","contribution":["contributedBy"]},{"name":"Martin Garrido","affiliation":"EMBL","email":"martin.garrido@embl.de","contribution":["contributedBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Sites (EMBL) dataset contains glycosylation information (mainly for N-glycosylation) on Mus musculus (taxid:10090) brain tissue proteins. The data is submitted by Dr. Clement Potel, Dr. Mira Burtscher and Dr. Martin Garrido, of the Genome Biology Unit, EMBL based on the publication 'Deep quantitative glycoproteomics reveals gut microbiome induced remodeling of the brain glycoproteome.' GlyTouCan accessions were mapped by the GlyGen team to the glycan compositions provided by the authors. If you use this dataset, please provide proper attribution to the data source [1], EMBL and GlyGen.","References: 1) Potel C, Burtscher ML, Garrido-Rodriguez M, Brauer-Nikonow A, Becher I, Typas A, Zimmermann M, Savitski M. Deep quantitative glycoproteomics reveals gut microbiome induced remodeling of the brain glycoproteome. bioRxiv 2023.09.13.557529; doi:10.1101/2023.09.13.557529."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[null]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"filename":"mouse_proteoform_glycosylation_sites_embl.csv","uri":"https://data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_embl.csv"}},{"mediatype":"csv","uri":{"filename":"mouse_proteoform_glycosylation_sites_embl.stat.csv","uri":"https://data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_embl.stat.csv"}}]},"etag":"b8b827c44d3d556b985cec7007fd94285646593ffd398a1f116612bd0e3176c3"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":899,"last_update":"2024-05-21T13:20:32.008698Z","access_count":10},{"object_id":"https://biocomputeobject.org/GLY_000890/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000890/DRAFT","etag":"8f05101ffb86405f0f50ede0715d07059f28eabca07b08c0c9263af2b2671a95","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Xref Glycan Array Data Repository","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.198Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Rene Ranzinger","affiliation":"University of Georgia","contribution":["contributedBy"],"email":"rene@ccrc.uga.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The dataset provides cross-references to the GlyGen Glycan Array Data Repository (https://glygen.ccrc.uga.edu/ggarray/) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GADR cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa domesticus"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepacivirus C"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GADR","Glycan Array Data Repository","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_gadr.csv","filename":"glycan_xref_gadr.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_gadr.stat.csv","filename":"glycan_xref_gadr.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":291,"last_update":"2024-05-17T11:24:17.198012Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000891/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000891/DRAFT","etag":"4d395f049e2c23c1acb161b602eed7cb9ce33e7f8e5d60ef95e40cfc277f2d78","spec_version":"1.3.0","provenance_domain":{"name":"Pig Reaction Participants (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T15:09:09.993Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Sus scrofa [taxid:9823] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_participants_reactome.csv","filename":"pig_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_participants_reactome.stat.csv","filename":"pig_protein_participants_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":368,"last_update":"2024-05-21T15:09:09.993102Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000892/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000892/DRAFT","etag":"a5b63ffd72d7a2e934db815c5c3ed76d6bdb93e14592fa404201400d819f66ee","spec_version":"1.3.0","provenance_domain":{"name":"Pig Reaction Participants (Rhea)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.279Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for pig [taxid:9823] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Participants","Reactions"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_participants_rhea.csv","filename":"pig_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_participants_rhea.stat.csv","filename":"pig_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":349,"last_update":"2024-05-17T11:24:17.279072Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000893/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000893/DRAFT","etag":"c1a242fa786a1d089d422584063ac711e00b97be748574fd25e59c1784a56686","spec_version":"1.3.0","provenance_domain":{"name":"Pig Glycosylation Sites (GlyConnect) ","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.316Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycosylation Sites (GlyConnect) dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions with information on reported glycans in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787). A json file was retrieved through GlyConnect API (https://glyconnect.expasy.org/api/glycosylations?taxonomy=Sus%20scrofa)"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLY_000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the latest UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (pig_proteoform_glycosylation_sites_glyconnect.1.log).","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_glyconnect.csv","filename":"pig_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"pig_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":344,"last_update":"2024-05-17T11:24:17.316941Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000894/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000894/DRAFT","etag":"d4da235ede684d347703d1400ddc66e09b1b2403f2a98aecfa53abbcf8ca1057","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Signal Peptide","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.356Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig Protein Signal Peptide dataset contains Sus scrofa [taxid:1758] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_annotation.csv","filename":"pig_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_peptidesequences.fasta","filename":"pig_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_cleavedsequences.fasta","filename":"pig_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_fullsequences.fasta","filename":"pig_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_annotation.stat.csv","filename":"pig_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_peptidesequences.stat.csv","filename":"pig_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_cleavedsequences.stat.csv","filename":"pig_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_signalp_fullsequences.stat.csv","filename":"pig_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":679,"last_update":"2024-05-17T11:24:17.356005Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000895/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000895/DRAFT","etag":"d88aefdea53733b5b9286ef9808b2069cbbbf1207578f4c70a942bcc65aab950","spec_version":"1.3.0","provenance_domain":{"name":"Pig Reactions (Rhea)","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by-sa/4.0/","created":"2021-06-03T17:38:21.320871","modified":"2024-05-17T11:24:17.395Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Luke Johnson ","affiliation":"The George Washington University","email":"luke.johnson@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Cyrus ","affiliation":"Au-Yeung","email":"cyruschauyeung@gwmail.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":[],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_reactions_rhea.csv","filename":"pig_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_reactions_rhea.stat.csv","filename":"pig_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:17.395896Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000896/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000896/DRAFT","spec_version":"1.3.0","etag":"9a261713c058ca9890a69124523f072374f122c55dc794f0b4ddd8116b5ce656","provenance_domain":{"name":"Pig Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T17:11:22.244Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycosylation Sites (UniProtKB) dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Sus scrofa proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_proteoform_glycosylation_sites_uniprotkb.csv","filename":"pig_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"pig_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":326,"last_update":"2024-12-10T17:11:22.244768Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000897/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000897/DRAFT","etag":"d5407f792281f64a905bb7f8c3d36fc469c22db73b832f5d43627a55a2148139","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Reactions (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:17.475Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Reactions (Reactome) dataset contains reactions information for pathways for Sus scrofa [taxid:9823] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_reactions_reactome.csv","filename":"pig_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_reactions_reactome.stat.csv","filename":"pig_protein_reactions_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":324,"last_update":"2024-05-17T11:24:17.475031Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000898/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000898/DRAFT","etag":"c2063d702a675d6dedb15123a1eb83dbe94d9e2092c369dd18e94a4065de85ae","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Binary Interactions (IntAct)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:17.512Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Binary Interaction (IntAct) dataset contains Sus scrofa [taxid:9823] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_binary_interactions.csv","filename":"pig_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_binary_interactions.stat.csv","filename":"pig_protein_binary_interactions.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":386,"last_update":"2024-05-17T11:24:17.512930Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000899/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000899/DRAFT","spec_version":"1.3.0","etag":"4800e377843262ae5c447bfae84ed55b82ffcd99be9f62a3b1ee078cb3e34021","provenance_domain":{"name":"Pig UniProtKB Xref O-GlcNAc (MCW)","version":"v-x.x.x","license":"httpss://creativecommons.org/licenses/by/4.0/","modified":"2024-07-29T19:50:11.777Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref O-GlcNAc (MCW) contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O-GlcNAc(MCW) is a database for O-GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["Pig","O-GlcNAc (MCW)","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_oglcnac_mcw.csv","filename":"pig_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_oglcnac_mcw.stat.csv","filename":"pig_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":355,"last_update":"2024-07-29T19:50:11.777260Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000900/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000900/DRAFT","etag":"12bce807ee17054d004f94653496b8333860a9d0ec6f3cfee7d66c1feccfb311","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:17.593Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref InterPro contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_interpro.csv","filename":"pig_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_interpro.stat.csv","filename":"pig_protein_xref_interpro.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":461,"last_update":"2024-05-17T11:24:17.593209Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000901/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000901/DRAFT","etag":"b024cbfb4bbef526be49255845b20ebe364cfa6338cbd8db96065c76ae2462ca","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref KEGG PATHWAY","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:17.630Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref KEGG PATHWAY contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen, KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"KEGG Pathway cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_kegg.csv","filename":"pig_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_kegg.stat.csv","filename":"pig_protein_xref_kegg.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":406,"last_update":"2024-05-17T11:24:17.630952Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000902/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000902/DRAFT","etag":"49f623fc524964ca7026f346ea3b4473df36bc9ab1db5e85a0d4380a785c1337","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref ChEMBL","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:17.672Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniprotKB Xref ChEMBL contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ChEMBL cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_chembl.csv","filename":"pig_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_chembl.stat.csv","filename":"pig_protein_xref_chembl.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":354,"last_update":"2024-05-17T11:24:17.672528Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000903/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000903/DRAFT","etag":"f5b0195ba9567d8709ebf8fe59c7b86d1178553a5199b61116308b208e38bddd","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref PRO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.711Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig UniprotKB Xref PRO contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRO cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_pro.csv","filename":"pig_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_pro.stat.csv","filename":"pig_protein_xref_pro.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":382,"last_update":"2024-05-17T11:24:17.711209Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000904/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000904/DRAFT","spec_version":"1.3.0","etag":"52986817a5f6e4e2b1fde306c798cf160e97d309536133569aa3658b6a153dcc","provenance_domain":{"name":"Pig Gene Symbols (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-12T17:00:53.817Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","email":"cyruschauyeung@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Pig Gene Symbols (NCBI RefSeq) dataset contains Sus scrofa [taxid:9823] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"pig_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_genenames_refseq.csv","filename":"pig_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_genenames_refseq.stat.csv","filename":"pig_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":244,"last_update":"2024-07-12T17:00:53.817487Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000905/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000905/DRAFT","etag":"2eeb133c40c815793d8de7ebf4273d4964dcb6fe365a5716808681c1bcad7447","spec_version":"1.3.0","provenance_domain":{"name":"Pig N-Glycosylation Sequon","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:03:35.493Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Sus scrofa [taxid:9823] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[{"uri":{"filename":"pig_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_canonicalsequences.fasta"}},{"uri":{"filename":"prosite.dat","uri":"https:/data.glygen.org/ln2downloads/prosite/prosite.dat"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_glycosylation_motifs.csv","filename":"pig_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_glycosylation_motifs.stat.csv","filename":"pig_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":333,"last_update":"2024-06-03T21:03:35.493221Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000906/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000906/DRAFT","etag":"51d6c3e0932942fddd50a1beeec2b978e1ab58ba99407edbfa9860d51c94a840","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref Pfam","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T15:58:30.083377","modified":"2024-05-17T11:24:17.828Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref Pfam contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_pfam.csv","filename":"pig_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_pfam.stat.csv","filename":"pig_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":384,"last_update":"2024-05-17T11:24:17.828596Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000907/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000907/DRAFT","etag":"eea937b532ea85e6e5447d5f8fa24f9bdf768f5b7fa7f6f300a0697e9189ca36","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.900608","modified":"2024-05-17T11:24:17.866Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Information dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_info_uniprotkb.csv","filename":"pig_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_info_uniprotkb.stat.csv","filename":"pig_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":277,"last_update":"2024-05-17T11:24:17.866776Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000908/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000908/DRAFT","etag":"39ceedaacf30bbe7f41601f4007fdd722c20ddc2af854973ca60899b0696e4d7","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref NCBI Gene","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.905Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref NCBI Gene dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_geneid.csv","filename":"pig_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_geneid.stat.csv","filename":"pig_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":501,"last_update":"2024-05-17T11:24:17.905006Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000909/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000909/DRAFT","etag":"12743b59d094e16bf0e49eb88b0545cf5dfc2ee507458c17255ebcff5022fc97","spec_version":"1.3.0","provenance_domain":{"name":"Pig Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T21:03:59.999Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Sus scrofa [taxid:9823] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_genenames_uniprotkb.csv","filename":"pig_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_genenames_uniprotkb.stat.csv","filename":"pig_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":401,"last_update":"2024-06-03T21:03:59.999695Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000910/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000910/DRAFT","etag":"c17de2e084d8a0212c13afdfcf46c6ca0652030f34ae72e1fa9842b101b665dd","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref OrthoDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:17.983Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref OrthoDB contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_orthodb.csv","filename":"pig_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_orthodb.stat.csv","filename":"pig_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2024-05-17T11:24:17.983393Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000911/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000911/DRAFT","etag":"45d6995a8e356c18f5514180f0b1cf900cbd3b0d934c17cd411e22f0b2f6b6ea","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Function (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.026Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Function (UniProtKB) dataset contains biological function annotation for Sus scrofa [taxid:9823] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_function_uniprotkb.csv","filename":"pig_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_function_uniprotkb.stat.csv","filename":"pig_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":253,"last_update":"2024-05-17T11:24:18.026225Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000912/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000912/DRAFT","spec_version":"1.3.0","etag":"06cef0b86dabbcd9c6e053cfd3134beb95297908c899bd50f2cee3daf7ada606","provenance_domain":{"name":"Pig Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-12T17:38:43.636Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","email":"cyruschauyeung@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Pig Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Sus scrofa [taxid:9823] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_altnames.csv","filename":"pig_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_altnames.stat.csv","filename":"pig_protein_altnames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":219,"last_update":"2024-07-12T17:38:43.636241Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000913/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000913/DRAFT","etag":"5bfd4c544bfcf170ec9f0eaf02551fa1100d84035d6d62892bb580b2106f1212","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Names (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.100Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Names (NCBI RefSeq) dataset contains Sus scrofa [taxid:9823] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"pig_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_proteinnames_refseq.csv","filename":"pig_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_proteinnames_refseq.stat.csv","filename":"pig_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":255,"last_update":"2024-05-17T11:24:18.100561Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000914/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000914/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:18.140Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Citations dataset contains publication information for Sus scrofa [taxid:9823] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"pig_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/compiled/pig_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_citations_uniprotkb.csv","filename":"pig_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_citations_uniprotkb.stat.csv","filename":"pig_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{},"etag":"75e467df443912c8b8b4901e3b4d2cb0fdbbe14ec20c46b5d6a2f77090579999"},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":412,"last_update":"2024-05-17T11:24:18.140558Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000915/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000915/DRAFT","etag":"79dca8de1dc3bff79ab2161e8860e1d315a1a61b3828e3daac94b19041da9497","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T20:31:01.317Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Canonical (UniProtKB) Sequences dataset contains Sus scrofa [taxid:9823] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all pig canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_canonicalsequences.fasta","filename":"pig_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_canonicalsequences.stat.csv","filename":"pig_protein_canonicalsequences.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":243,"last_update":"2024-06-03T20:31:01.317369Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000916/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000916/DRAFT","etag":"e32433290a5be1062ed04c0b9ab3f99c1c319c3dfe1d6f1b37b5d299993e8e18","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.221Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref PDB contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_pdb.csv","filename":"pig_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_pdb.stat.csv","filename":"pig_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":385,"last_update":"2024-05-17T11:24:18.221006Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000917/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000917/DRAFT","etag":"d93e30e0d3926454b70f64acc25e80ffce0b37da1134f720dd46dc2da031bb44","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.259Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Isoform sequences (UniProtKB) dataset contains Sus scrofa [taxid:9823] protein fasta sequences for the pig isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all pig isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_allsequences.fasta","filename":"pig_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_allsequences.stat.csv","filename":"pig_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":262,"last_update":"2024-05-17T11:24:18.259582Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000918/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000918/DRAFT","etag":"864df1a363165bb141dca3d77548bf7faa33c1bfa979845a266813fed7f101d2","spec_version":"1.3.0","provenance_domain":{"name":"Dicty NCBI Protein Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T15:53:48.568Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty NCBI Protein Linkouts contains Dictyostelium discoideum [taxid:44689] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"dicty_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"dicty_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_ncbi_linkouts.csv","filename":"dicty_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_ncbi_linkouts.stat.csv","filename":"dicty_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":265,"last_update":"2024-05-21T15:53:48.568291Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000919/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000919/DRAFT","etag":"0b0e93076a35995b790d99aed78f4a9285b7fbd30bf70ac5d29d60890e463a3b","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref Bgee","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.338Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref Bgee dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_bgee.csv","filename":"pig_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_bgee.stat.csv","filename":"pig_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":467,"last_update":"2024-05-17T11:24:18.338250Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000920/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000920/DRAFT","etag":"093ca88dcdf28b22e3a21d42e6adf440dc454911bd0c46dfec9fe1ecc1b411b6","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:42:17.034Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref (UniProtKB) dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_uniprotkb.csv","filename":"pig_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_uniprotkb.stat.csv","filename":"pig_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":250,"last_update":"2024-05-21T14:42:17.034864Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000921/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000921/DRAFT","etag":"b5aa4b67d9fc8b3aff059ce5c3808182b78e15666a020684fde5ac1a319b81a3","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref Reactome","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.419Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref Reactome contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_reactome.csv","filename":"pig_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_reactome.stat.csv","filename":"pig_protein_xref_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":343,"last_update":"2024-05-17T11:24:18.419030Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000922/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000922/DRAFT","etag":"1e39c34af1db377ef8223688068496e98a298b939aca889c8f9fff3fb4fd01f6","spec_version":"1.3.0","provenance_domain":{"name":"Human Glycogenes (GlycoEnzOnto)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.456Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":[""],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycogenes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["glycogenes","enzymes"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_glycogenes_glycoenzonto.csv","filename":"human_protein_glycogenes_glycoenzonto.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_glycogenes_glycoenzonto.stat.csv","filename":"human_protein_glycogenes_glycoenzonto.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T11:24:18.456778Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000923/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000923/DRAFT","etag":"8e498f77a94e5fd0d8138908031cea20b5c68ba57c40662edbed56dec5b2ae29","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Sequence Info (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.494Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Sequence Info (UniProtKB) dataset contains Sus scrofa [taxid:9823] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all pig isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_sequenceinfo.csv","filename":"pig_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_sequenceinfo.stat.csv","filename":"pig_protein_sequenceinfo.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":268,"last_update":"2024-05-17T11:24:18.494936Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000924/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000924/DRAFT","spec_version":"1.3.0","etag":"1743b1c22c7f8a87475ab997e2a25e36eafac1fa4f3ce4b143e9c027e3a11c0c","provenance_domain":{"name":"Pig Proteoform Glycosylation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by-sa/4.0/","created":"2021-06-03T16:32:02.053252","modified":"2025-10-09T15:00:51.384Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Proteoform Glycosylation Citations (UniProtKB) dataset contains Sus scrofa [taxid:9823] citation details of the publications present in the dataset Pig Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000896)."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"pig_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"pig_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":279,"last_update":"2025-10-09T15:00:51.384634Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000925/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000925/DRAFT","spec_version":"1.3.0","etag":"260668271c9da130d6048b120f0ff207bd3e4070b1f1e01edc1555492992d8cc","provenance_domain":{"name":"Pig EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-04T15:46:41.405Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig EBI-UniProtKB NT file contains proteome data for Sus scrofa [taxid:9823] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}],"keywords":["NT","proteome","EMBL-EBI"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_ntdata.nt","filename":"pig_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_ntdata.stat.csv","filename":"pig_protein_ntdata.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":325,"last_update":"2025-03-04T15:46:41.405014Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000926/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000926/DRAFT","etag":"921c748d91d392ca5bdc3c5d75df2f0f66f9dd724707c4f5052ce4be43c3d559","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein PTM Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.609Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein PTM Annotation (UniProtKB) dataset contains Sus scrofa [taxid:9823] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_ptm_annotation_uniprotkb.csv","filename":"pig_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_ptm_annotation_uniprotkb.stat.csv","filename":"pig_protein_ptm_annotation_uniprotkb.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":307,"last_update":"2024-05-17T11:24:18.609650Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000927/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000927/DRAFT","etag":"e1b0acc490dc35b67827982a28b06d7d63e70a4475d6b84f68c5f717de6616fd","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref OMA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.652Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref OMA contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"OMA cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_oma.csv","filename":"pig_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_oma.stat.csv","filename":"pig_protein_xref_oma.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2024-05-17T11:24:18.652022Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000928/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000928/DRAFT","spec_version":"1.3.0","etag":"c4af90af465dc665bc9d160dde505ad662f0dba27ba45190fa3011b15e0bd10b","provenance_domain":{"name":"Pig Proteoform Phosphorylation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T08:00:04.645468","modified":"2025-10-09T14:41:19.701Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Proteoform Phosphorylation Citations (UniProtKB) dataset contains Sus scrofa [taxid:9823] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"pig_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"pig_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":339,"last_update":"2025-10-09T14:41:19.701985Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000929/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000929/DRAFT","etag":"d210e9645d74a8a0280fcff428643a548dd62a2169d987fdddc3fd7e3618e449","spec_version":"1.3.0","provenance_domain":{"name":"Pig Transcript Locus (Ensembl Transcript coordinates)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.733Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB Sus scrofa [taxid:9823] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. ","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_transcriptlocus.csv","filename":"pig_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_transcriptlocus.stat.csv","filename":"pig_protein_transcriptlocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":383,"last_update":"2024-05-17T11:24:18.733696Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000930/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000930/DRAFT","etag":"d2229dc2cac4ef2743a5b328539a769e1051f62185eb16b52172a5c658224b24","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Citations (RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.771Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Citations (RefSeq) datasets contains Sus scrofa [taxid:9823] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions.  If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_refseq.csv","filename":"pig_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_refseq.stat.csv","filename":"pig_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":308,"last_update":"2024-05-17T11:24:18.771893Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000931/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000931/DRAFT","etag":"4daca4c0324523a11e8ab415dde569622f0432a64425e3ef9aae42198d6e4889","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref PANTHER","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.809Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref PANTHER contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PANTHER cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_panther.csv","filename":"pig_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_panther.stat.csv","filename":"pig_protein_xref_panther.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":461,"last_update":"2024-05-17T11:24:18.809571Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000932/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000932/DRAFT","spec_version":"1.3.0","etag":"b6b566e1ff1de4fe90e4e39c664fd0a8330fad4ddcbf0c77affd6e0d40c41c35","provenance_domain":{"name":"Pig NCBI Protein Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-03-20T15:53:27.297125","modified":"2025-10-09T15:04:22.208Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig NCBI Protein Linkouts contains Sus scrofa [taxid:1758] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}],"keywords":["NCBI Protein Linkouts","RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_ncbi_linkouts.csv","filename":"pig_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_ncbi_linkouts.stat.csv","filename":"pig_protein_ncbi_linkouts.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":302,"last_update":"2025-10-09T15:04:22.208944Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000933/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000933/DRAFT","etag":"df27320db84a5450d3acf3240b74ce8a26f2c22026cc635cf0bf0d37645aa457","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.887Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref Rhea contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"RHEA cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_rhea.csv","filename":"pig_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_rhea.stat.csv","filename":"pig_protein_xref_rhea.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":242,"last_update":"2024-05-17T11:24:18.887267Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000934/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000934/DRAFT","etag":"352ad004a39ed25d7d14ace022c564fbe68c9798fd5a1d57ae8ca52b54ea5826","spec_version":"1.3.0","provenance_domain":{"name":"Pig Pathways (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:18.927Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_pathways_reactome.csv","filename":"pig_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_pathways_reactome.stat.csv","filename":"pig_protein_pathways_reactome.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":92,"last_update":"2024-05-17T11:24:18.927447Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000935/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000935/DRAFT","etag":"41bf63bbb9fbc616809e1db3aa8ac5bc5513d6d74aaa2010202d1679383e00e5","spec_version":"1.3.0","provenance_domain":{"name":"Pig O-GlcNAc Glycosylation Sites (MCW)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:18.965Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig O-GlcNAc Glycosylation Sites (MCW) contains Sus scrofa (taxid:9823) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Pig O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen's pig protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to pig species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen's fasta sequence for the corresponding pig UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein's O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"pig_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"pig_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":2453,"last_update":"2024-05-17T11:24:18.965370Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000936/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000936/DRAFT","etag":"139c4840cd634c40edfab0430291f9671a6ed226a3731263c49dcd6402772460","spec_version":"1.3.0","provenance_domain":{"name":"Pig Gene Locus (Ensembl)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.005Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Gene Locus (Ensembl) contains Sus scrofa [taxid:9823] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_genelocus.csv","filename":"pig_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_genelocus.stat.csv","filename":"pig_protein_genelocus.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":307,"last_update":"2024-05-17T11:24:19.005517Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000937/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000937/DRAFT","etag":"6bc38ec634a4cad68d63b11defdbf943df0c0d7a693b69227b36b16b78099591","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Recommended Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.956673","modified":"2024-05-21T14:11:01.148Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Sus scrofa [taxid:1758] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_recnames.csv","filename":"pig_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_recnames.stat.csv","filename":"pig_protein_recnames.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":220,"last_update":"2024-05-21T14:11:01.148990Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000938/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000938/DRAFT","etag":"a25364087b5590ec415d156fe9fc9231c9aacc89cc008b5231a9aa5605b544e0","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Function (NCBI Refseq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":[],"created":"","modified":"2024-05-17T11:24:19.087Z","review":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Function (NCBI RefSeq) dataset contains biological function annotation of Sus scrofa [taxid:9823] genes from GeneRIF section in the NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_function_refseq.csv","filename":"pig_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_function_refseq.stat.csv","filename":"pig_protein_function_refseq.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":254,"last_update":"2024-05-17T11:24:19.087379Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000939/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000939/DRAFT","etag":"dafa3714330f11e37657065a98812081cf34ee976abdbd3ab7647b086a9ccc25","spec_version":"1.3.0","provenance_domain":{"name":"Pig Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-x.x.x","license":"httpss://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.127Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Pig O-GlcNAc Glycosylation Sites (MCW)  httpss://data.glygen.org/GLY_000935, contributed by Stephanie Olivier's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed","MCW","Glycosylation"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"pig_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"pig_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":232,"last_update":"2024-05-17T11:24:19.127972Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000940/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000940/DRAFT","spec_version":"1.3.0","etag":"7b833a4aa0596077e78fb3a924701c1c0002118fda4d9f97647e273ece96924d","provenance_domain":{"name":"Pig UniProtKB xref GlyConnect","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-03T03:58:28.936Z","modified":"2024-12-10T17:14:26.652Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Pig UniProtKB xref GlyConnect dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pigprotein_xref_glyconnect.csv","filename":"pig_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_glyconnect.stat.csv","filename":"pig_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":162,"last_update":"2024-12-10T17:14:26.652849Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000941/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000941/DRAFT","etag":"8c5a07348760eb38db1e08bda4c83909ac9f051e80b05310aa8ad734ca59d686","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref CDD","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T12:09:02.680538","modified":"2024-05-17T11:24:19.206Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig UniProtKB Xref CDD contains Sus scrofa [taxid:1758] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_cdd.csv","filename":"pig_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_cdd.stat.csv","filename":"pig_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":417,"last_update":"2024-05-17T11:24:19.206793Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000942/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000942/DRAFT","etag":"f47a9471160f22c68de81e9ff4aa30fce0e4a1f52f9b72ef44bd6d674b4106d4","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref BRENDA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.961796","modified":"2024-05-17T11:24:19.246Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig UniprotKB Xref BRENDA contains Sus scrofa [taxid:9606] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_brenda.csv","filename":"pig_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_brenda.stat.csv","filename":"pig_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":473,"last_update":"2024-05-17T11:24:19.246249Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000943/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000943/DRAFT","spec_version":"1.3.0","etag":"10957206fed88a36c064627ec22ad537bbfda4551165e4e9d75fc6d886dff9c7","provenance_domain":{"name":"Pig Protein Site Annotation","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-12-01T15:29:48.229274","modified":"2025-10-09T15:07:11.153Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Site Annotation (UniProtKB) dataset contains Sus scrofa [taxid:1758] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}],"keywords":["site annotation","amino acid range","UniProtKB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_site_annotation_uniprotkb.csv","filename":"pig_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_site_annotation_uniprotkb.stat.csv","filename":"pig_protein_site_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":373,"last_update":"2025-10-09T15:07:11.153957Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000944/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000944/DRAFT","etag":"17abc304c8fe7c96418062a01770ba6894aa408ba75a4122b0b727889dfb0720","spec_version":"1.3.0","provenance_domain":{"version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-23T17:58:12.089Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Protein Reactions (Reactome) dataset contains reactions information for pathways for Sus scrofa [taxid:9823] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":324,"last_update":"2024-05-23T17:58:12.089798Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_000945/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000945/DRAFT","etag":"b3935913b41f479a14bab7fae626baf8709b2f7470908362df692f679fba3979","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Submitted Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.362Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Sus scrofa [taxid:9823] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_submittednames.csv","filename":"pig_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_submittednames.stat.csv","filename":"pig_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":504,"last_update":"2024-05-17T11:24:19.362638Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000946/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000946/DRAFT","etag":"e038c8add93bfa3e5ac32fb8e9a636f367f66fa73632d8a3dd2c26a8982580b9","spec_version":"1.3.0","provenance_domain":{"name":"Pig Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.401Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","affiliation":"","contribution":["contributedBy"],"email":""},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig Protein Information (NCBI RefSeq) dataset contains Sus scrofa [taxid:9823] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_info_refseq.csv","filename":"pig_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_info_refseq.stat.csv","filename":"pig_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":282,"last_update":"2024-05-17T11:24:19.401901Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000947/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000947/DRAFT","etag":"afc0fb5922d46ebc6cfc24355b6e117c288010d7bde4b7ac61444be721816c2a","spec_version":"1.3.0","provenance_domain":{"name":"Pig Phosphorylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.439Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig Phosphorylation Sites (UniProtKB) dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"pig_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"pig_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":306,"last_update":"2024-05-17T11:24:19.439713Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000948/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000948/DRAFT","etag":"539424d21afb4eaf551620995463f039d1d0241ef6a01759d30def9886183062","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref IntAct","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.480Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig UniProtKB Xref IntAct dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_intact.csv","filename":"pig_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_intact.stat.csv","filename":"pig_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":525,"last_update":"2024-05-17T11:24:19.480767Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000949/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000949/DRAFT","etag":"0b096491a78cdf4e5a2cf8cd91b16219fb622d174d1bc42243e7c3e6531c8337","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref CAZy","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.520Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig UniprotKB Xref CAZy contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_cazy.csv","filename":"pig_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_cazy.stat.csv","filename":"pig_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":462,"last_update":"2024-05-17T11:24:19.520918Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000950/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000950/DRAFT","etag":"95f89a109eb624444c4af2af2322f9d6f8a17e910b8d6bdbf62aeb06203278ff","spec_version":"1.3.0","provenance_domain":{"name":"Pig Proteome Masterlist (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T20:31:26.641Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Proteome Masterlist dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_masterlist.csv","filename":"pig_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_masterlist.stat.csv","filename":"pig_protein_masterlist.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":288,"last_update":"2024-06-03T20:31:26.641913Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000951/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000951/DRAFT","spec_version":"1.3.0","etag":"0e034c6a14aba50a058a805b4ed7b15d4783c54a14e9392bb309bc0b4c5e4030","provenance_domain":{"name":"Pig UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-09T14:04:02.759Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniprotKB Xref RefSeq contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein accessions","RefSeq","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_refseq.csv","filename":"pig_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_xref_refseq.stat.csv","filename":"pig_protein_xref_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":763,"last_update":"2025-10-09T14:04:02.759462Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000952/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000952/DRAFT","etag":"1ef6346a16a4f28ff439b98abd3bf4b6b1a2c15c2cd7547697675726cb66a5b3","spec_version":"1.3.0","provenance_domain":{"name":"Pig Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.634Z","derived_from":[],"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"review":[]},"usability_domain":["The Pig Gene Ontology (GO) dataset contains Sus scrofa [taxid:9823] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_go_annotation.csv","filename":"pig_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_go_annotation.stat.csv","filename":"pig_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":259,"last_update":"2024-05-17T11:24:19.634785Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_000953/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000953/DRAFT","spec_version":"1.3.0","etag":"90a5a1675c52047a81853dd7d470138856cabe5d8dbb3f453a8934af6276a9b8","provenance_domain":{"name":"Pig Proteoform Citations (GlyConnect)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-05T19:25:52.754Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID). The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}],"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"pig_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"pig_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":475,"last_update":"2024-12-05T19:25:52.754933Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000954/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000954/DRAFT","spec_version":"1.3.0","etag":"795fd69ce64710e18e6fd7e3388e7a4f65cb76698a5e18dcf7b4f916131900aa","provenance_domain":{"name":"Pig UniProtKB Xref O-GlcNAcAtlas","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-08-19T10:24:35.912Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref O-GlcNAcAtlas dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to O-GlcNAcAtlas database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAcAtlas and GlyGen. O-GlcNAcAtlas is a a rigorously curated database for experimentally identified O-GlcNAc sites/proteins (https://oglcnac.org/atlas/)"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAcAtlas database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["Cross-references","O-GlcNAcAtlas"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_oglcnac_atlas.csv","filename":"pig_protein_xref_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_oglcnac_atlas.stat.csv","filename":"pig_protein_xref_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":479,"last_update":"2026-08-19T10:24:35.912530Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000955/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000955/DRAFT","etag":"bde9267f2ba4eac618e34bd2c458f8d7c3ff99a570f7c833c126911b3c4ff44f","spec_version":"1.3.0","provenance_domain":{"name":"Pig O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.755Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","orcid":"","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Sus scrofa (taxid:9823) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Serine","Threonine"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"pig_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"pig_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":279,"last_update":"2024-05-17T11:24:19.755005Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000956/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000956/DRAFT","etag":"ecca535ab8100a9b85de3d930a3e4c64e28fed645b0ef2e22e15bcf0a9c0f599","spec_version":"1.3.0","provenance_domain":{"name":"Pig O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-2.4.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2024-05-17T11:24:19.794Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","orcid":"","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Pig O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000955, contributed by Jungfeng Ma's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"pig_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"pig_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":247,"last_update":"2024-05-17T11:24:19.794489Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000957/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000957/DRAFT","etag":"617dee8e1caebba2e681011ea1740a81f2cbf91b43fd0f0c557a71a293207b3f","spec_version":"1.3.0","provenance_domain":{"name":"Pig Glycohydrolases","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.892318","modified":"2024-05-21T16:00:32.801Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycohydrolases dataset contains a list of Sus scrofa [taxid:9823] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"pig_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/compiled/pig_protein_glycohydrolase.csv"}},{"uri":{"filename":"pig_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_glycohydrolase.csv","filename":"pig_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_glycohydrolase.stat.csv","filename":"pig_protein_glycohydrolase.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":282,"last_update":"2024-05-21T16:00:32.801835Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000958/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000958/DRAFT","etag":"718723fdec84f021a83fe01b61b7e148425732bef6f3a1d97af15d26cd36c748","spec_version":"1.3.0","provenance_domain":{"name":"Pig Glycosyltransferases","version":"v-2.3.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.870634","modified":"2024-05-21T15:59:13.962Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Hayley Dingerdissen","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"hmhamilt@gwmail.gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycosyltransferases dataset contains list of Sus scrofa [taxid:9823] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the pig proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Sus scrofa (Pig) [9823]\". To retrieve the list of all pig glycosyltransferases, the full list of pig proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"pig_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/compiled/pig_protein_glycosyltransferase.csv"}},{"uri":{"filename":"pig_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_glycosyltransferase.csv","filename":"pig_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/pig_protein_glycosyltransferase.stat.csv","filename":"pig_protein_glycosyltransferase.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":1978,"last_update":"2024-05-21T15:59:13.962138Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_000959/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000959/DRAFT","spec_version":"1.3.0","etag":"434ad2f0319aea59cb2f129b2ac72f6be4b6fe35ab9f0bbe2eacc96563a72962","provenance_domain":{"name":"Chicken O-GlcNAc Glycosylation Sites (MCW)","version":"v-2.4.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:48:29.540934","modified":"2024-06-25T21:10:51.241Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken O-GlcNAc Glycosylation Sites (MCW) contains Gallus gallus(taxid:9031) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Chicken O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s chicken protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to chicken species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding chicken UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"chicken_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"chicken_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":2476,"last_update":"2024-06-25T21:10:51.241642Z","access_count":12},{"object_id":"https://biocomputeobject.org/GLY_000960/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000960/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Human Glycosylation Sites Diabetes Glycomics Study","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-04T13:24:39.398Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Olga Gornik","affiliation":"University of Zagreb","email":"ogornik@pharma.hr","contribution":["contributedBy"]},{"name":"Nadja Rudman","affiliation":"University of Zagreb","email":"najda.rudman@gmail.com","contribution":["contributedBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites Diabetes Glycomics Study dataset contains abundance information on the plasma N-glycome of individuals participating in the FinRisk study. Baseline samples were analyzed from 37 individuals who developed type 2 diabetes within 10 years and 37 sex and age matched individuals who remained normoglycaemic. HILIC-UPLC chromatograms were separated into 46 peaks, and were assigned to the most abundant glycan structures in each peak (see Fig 1 of Ref. 1). The data is submitted by Dr. Olga Gornik, Faculty of Pharmacy and Biochemistry, University of Zagreb. GlyTouCan accessions were mapped to each peak by the GlyGen team based on the glycan topology. If you use this dataset please provide proper attribution to the source publication [1] and GlyGen.","References: 1) Keser T, Gornik I, Vučković F, Selak N, Pavić T, Lukić E, Gudelj I, Gašparović H, Biočina B, Tilin T, Wennerström A, Männistö S, Salomaa V, Havulinna A, Wang W, Wilson JF, Chaturvedi N, Perola M, Campbell H, Lauc G, Gornik O. Increased plasma N-glycome complexity is associated with higher risk of type 2 diabetes. Diabetologia. 2017;60(12):2352-2360. doi:10.1007/s00125-017-4426-9. PMID:28905229."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Diabetes glycomic study","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["N-glycome","Publications","Citations","PubMed","Diabetes"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script performs QC steps and creates a proteoform dataset according to the GlyGen data model."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glyosylation_sites_diabetes_glycomic.csv","filename":"human_proteoform_glycosylation_sites_diabetes_glycomic.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glyosylation_sites_diabetes_glycomic.stat.csv","filename":"human_proteoform_glycosylation_sites_diabetes_glycomic.stat.csv"}}]},"etag":"2c65f7cc9c4e18834bc8de8dccb2cc089e2cac33e79517f8cc3425c55a60fcd0"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":1190,"last_update":"2024-06-04T13:24:39.398874Z","access_count":14},{"object_id":"https://biocomputeobject.org/GLY_000961/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000961/DRAFT","spec_version":"1.3.0","etag":"be229a3804bc8119840b267bfc89ac067415439833dd7a04e99e393d5a3ba7ec","provenance_domain":{"name":"Human Glycosylation Sites ccRCC (PDC)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-23T00:39:27","modified":"2024-07-23T00:40:06.813Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites (PDC) dataset contains glycosylation information and intact glycopeptide abundances from Homo sapiens (taxid:9606) clear cell renal cell carcinoma (ccRCC) tumor and normal adjacent tissues collected by the CPTAC program. The processed data was retrieved from the Proteomic Data Commons (PDC) and can be accessed at https://proteomic.datacommons.cancer.gov/pdc/study/PDC000471. GlyTouCan and UniProtKB accessions were mapped by the GlyGen team to the glycan compositions and gene names provided by the authors, respectively. If you use this dataset please provide proper attribution to the source publication[1], PDC and GlyGen.","References: 1) Lih TM, Cho KC, Schnaubelt M, Hu Y, Zhang H. Integrated glycoproteomic characterization of clear cell renal cell carcinoma. Cell Rep. 2023 May 30;42(5):112409. doi: 10.1016/j.celrep.2023.112409. Epub 2023 Apr 18. PMID: 37074911; PMCID: PMC10247542."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script performs QC steps and creates a proteoform dataset according to the GlyGen data model."}],"keywords":["N-linked glycosylation","glycoproteomics","clear cell renal cell carcinoma","PDC"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_pdc_ccrcc.csv","filename":"human_proteoform_glycosylation_sites_pdc_ccrcc.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_pdc_ccrcc.stat.csv","filename":"human_proteoform_glycosylation_sites_pdc_ccrcc.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites ccRCC (PDC)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":920,"last_update":"2024-07-23T00:40:06.813635Z","access_count":13},{"object_id":"https://biocomputeobject.org/GLY_000962/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000962/DRAFT","spec_version":"1.3.0","etag":"e778e9f81883a39e67b0cdfcc477ac0233fd6dc971263270a8b13dc96f619af6","provenance_domain":{"name":"Chicken O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-2.4.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-06-25T21:16:42.436Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Gallus gallus (taxid:9031) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":["O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"chicken_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"chicken_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":286,"last_update":"2024-06-25T21:16:42.436481Z","access_count":16},{"object_id":"https://biocomputeobject.org/GLY_000964/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000964/DRAFT","spec_version":"1.3.0","provenance_domain":{"version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T15:58:30.083377","modified":"2024-05-23T17:58:24.938Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref Pfam contains pig [taxid:9823] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"error_domain":{},"etag":"d74ce3700c5f0b8db579f692a11019a1a92a2b1740dfa09e85b35fb0ce8d8b5f"},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":432,"last_update":"2024-05-23T17:58:24.938615Z","access_count":14},{"object_id":"https://biocomputeobject.org/GLY_000965/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000965/DRAFT","spec_version":"1.3.0","etag":"0e9ad537095d5da537056ee7ea3c15cb8fb0f7ee9397e59116969826f4e26b09","provenance_domain":{"name":"Chicken Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.905721","modified":"2024-12-10T17:08:58.974Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosylation Sites (UniProtKB) dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Gallus gallus proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_19/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_uniprotkb.csv","filename":"chicken_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"chicken_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":338,"last_update":"2024-12-10T17:08:58.974182Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000966/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000966/DRAFT","etag":"c292842856ab788b3a25a8743463a6d4c975624b5a04a3f24ab5e0fae7f5ea31","spec_version":"1.3.0","provenance_domain":{"name":"Chicken NCBI Protein Linkouts","version":"v-2.4.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-03-20T15:53:27.297125","modified":"2024-05-21T15:54:17.755Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken NCBI Protein Linkouts contains Gallus gallus [taxid:9031] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"chicken_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_ncbi_linkouts.csv","filename":"chicken_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_ncbi_linkouts.stat.csv","filename":"chicken_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":255,"last_update":"2024-05-21T15:54:17.755675Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000967/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000967/DRAFT","etag":"9d00500bb5409eb26edafe03635ecb223a47e034ffa56455a2983749b92852ae","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Gene Locus (Ensembl)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.950210","modified":"2024-05-21T15:48:56.218Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Gene Locus (Ensembl) contains Gallus gallus [taxid:9031] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_masterlist.csv"}},{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_genelocus.csv","filename":"chicken_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_genelocus.stat.csv","filename":"chicken_protein_genelocus.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":314,"last_update":"2024-05-21T15:48:56.218132Z","access_count":9},{"object_id":"https://biocomputeobject.org/GLY_000968/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000968/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Pathways (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T15:38:19.862Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Pathways (Reactome) dataset contains Gallus gallus [taxid:9031] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database"],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions  from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_pathways_reactome.csv","filename":"chicken_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_pathways_reactome.stat.csv","filename":"chicken_protein_pathways_reactome.stat.csv"}}]},"etag":"b0b8fd6ce2a47177d60391b525c7ac40c899cec215b8581e110ab13500eff0a4"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":362,"last_update":"2024-05-21T15:38:19.862094Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000969/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000969/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref PANTHER","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:21:36.037Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref PANTHER contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_panther.csv","filename":"chicken_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_panther.stat.csv","filename":"chicken_protein_xref_panther.stat.csv"}}]},"error_domain":{},"etag":"9f4be5c47e8c60c136a7dc3d630dff37905d49e92602d735a4e60e0cee3a665e"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":466,"last_update":"2024-05-21T14:21:36.037317Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000970/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000970/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref OMA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:22:10.844Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref OMA contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_oma.csv","filename":"chicken_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_oma.stat.csv","filename":"chicken_protein_xref_oma.stat.csv"}}]},"error_domain":{},"etag":"8c45247d23e2f924007b29124250cac421601fd3a338cae676d40dbc433ebdc3"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-05-21T14:22:10.844783Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000971/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000971/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:22:39.804Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Canonical (UniProtKB) Sequences dataset contains Gallus gallus [taxid:9031] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all chicken canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_canonicalsequences.fasta","filename":"chicken_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_canonicalsequences.stat.csv","filename":"chicken_protein_canonicalsequences.stat.csv"}}]},"error_domain":{},"etag":"74c74f50476496aa95702dc27214b3ea53d93de0a4a628ac7dd541110f511567"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":249,"last_update":"2024-05-21T14:22:39.804127Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000972/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000972/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken N-Glycosylation Sequon","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:23:10.443Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Gallus gallus [taxid:9031] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_glycosylation_motifs.csv","filename":"chicken_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_glycosylation_motifs.stat.csv","filename":"chicken_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{},"etag":"397762d9b0fc4578071f167ffef824a939c607f742f6af7e31775e64f0822f62"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":340,"last_update":"2024-05-21T14:23:10.443362Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_000973/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000973/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB xref GlyConnect","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T15:36:58.678Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Chicken UniProtKB xref GlyConnect dataset contains Gallus gallus (taxid: 9031) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Xref","GlyConnect"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_glyconnect.csv","filename":"chicken_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_glyconnect.stat.csv","filename":"chicken_protein_xref_glyconnect.stat.csv"}}]},"etag":"7563ca70c01804a5331459efc1eedbb14cfce096b444ec7e63a54ee579d86a34"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":139,"last_update":"2024-05-21T15:36:58.678448Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000974/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000974/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref PRO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:23:43.807Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniprotKB Xref PRO contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_pro.csv","filename":"chicken_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_pro.stat.csv","filename":"chicken_protein_xref_pro.stat.csv"}}]},"error_domain":{},"etag":"e64b092e34cc75f16fb950eb1597bba7c0991f5e8ffc978fdcbe65c993b4e825"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2024-05-21T14:23:43.807956Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000975/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000975/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Binary Interactions (IntAct)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:24:05.341Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Binary Interaction (IntAct) dataset contains Gallus gallus [taxid:9031] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc.  If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","input_list":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_binary_interactions.csv","filename":"chicken_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_binary_interactions.stat.csv","filename":"chicken_protein_binary_interactions.stat.csv"}}]},"error_domain":{},"etag":"936807f163cc90c19f7ec1bc8e61e0c8511af008fc01d9083b326fe8bb88135d"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":393,"last_update":"2024-05-21T14:24:05.341973Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000976/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000976/DRAFT","spec_version":"1.3.0","provenance_domain":{"version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-04T14:41:24.656Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"George Washington University","contribution":["createdBy"],"email":"rykahsay@email.gwu.edu"},{"name":"Vijay Shanker","affiliation":"University of Delaware","contribution":["contributedBy"],"email":"vijay@udel.edu"},{"name":"Karen Ross","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"ker25@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Gallus gallus [taxid:9031] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000998)"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv"}]},"error_domain":{},"etag":"76f9566d4c0d86ab5f94a038e10f4c70a2ecb2c480a9beb92181df5dca2fc367"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":450,"last_update":"2024-06-04T14:41:24.656557Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000977/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000977/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Protein Resource Ontology [Chicken]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T15:24:48.377Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Darren Natale","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"dan5@georgetown.edu"},{"name":"Matthew Campbell ","affiliation":"UniCarbKB","contribution":["contributedBy"],"email":"m.campbell2@griffith.edu.au"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for Gallus gallus [taxid:9031] proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_pro_annotation.csv","filename":"chicken_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_pro_annotation.stat.csv","filename":"chicken_protein_pro_annotation.stat.csv"}}]},"error_domain":{},"etag":"3fb323c2080b7f434dcce6642c62afc63250eccdfb0908c554afb7b570e76e45"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":237,"last_update":"2024-05-21T15:24:48.377188Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000978/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000978/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref OrthoDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:24:30.413Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref OrthoDB contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_orthodb.csv","filename":"chicken_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_orthodb.stat.csv","filename":"chicken_protein_xref_orthodb.stat.csv"}}]},"error_domain":{},"etag":"8e0f5d0c81cbc620851f74e5a67274ea27d51f4154a5c85a360cf107f16d175b"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":427,"last_update":"2024-05-21T14:24:30.413254Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000979/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000979/DRAFT","etag":"b0b0f40f2bbe48f0fb6188868a6ca46e34ac11b6aeefc5dcb9781c6758ab3ddc","spec_version":"1.3.0","provenance_domain":{"version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-06-14T14:54:26.195339","modified":"2024-05-23T17:58:45.943Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","contribution":["contributedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides information on N-glycosylation sites on Chicken proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Winiewski, J. R., & Mann, M. (2012). Quantification of the N-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Chicken Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\").  The listed proteins (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB publications","category_name":"tag"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]}}],"description_domain":{"keywords":["proteins","canonical","glycosylation","literature","publications"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLYDS000002)to generate the output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"value":""}],"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":825,"last_update":"2024-05-23T17:58:45.943337Z","access_count":11},{"object_id":"https://biocomputeobject.org/GLY_000980/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000980/DRAFT","spec_version":"1.3.0","etag":"abc2aecf245568d73aca71da297b6903eaa4da7c2dc567f82c26cb5211a5f231","provenance_domain":{"name":"Chicken Glycosylation Sites (GlyConnect) ","version":"v-2.4.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-02-10T10:16:50.152756","modified":"2024-08-29T22:02:13.785Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosylation Sites (GlyConnect) dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Gallus gallus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (chicken_proteoform_glycosylation_sites_glyconnect.1.log)"}],"keywords":["glycosylation","reported glycosylation"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt"}},{"uri":{"filename":"glyconnect_chicken.json","uri":"https:/data.glygen.org/ln2downloads/glyconnect/2024_02_01/glyconnect_chicken.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_glyconnect.csv","filename":"chicken_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"chicken_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":635,"last_update":"2024-08-29T22:02:13.785550Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000982/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000982/DRAFT","spec_version":"1.3.0","etag":"254aaef081cb54c6d1ec4b905f8b832a0cc9e877d171f2461161c80724044089","provenance_domain":{"name":"Chicken Proteoform Phosphorylation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T08:00:04.645468","modified":"2025-10-09T14:43:47.001Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Proteoform Phosphorylation Citations (UniProtKB) dataset contains Gallus gallus [taxid:9606] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"chicken_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"chicken_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2025-10-09T14:43:47.001224Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000983/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000983/DRAFT","etag":"e79707e51ea4bb082c3376e90d577541f02b280579435852a96dc89a6809aa43","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T16:20:41.396963","modified":"2024-05-21T15:15:18.502Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniprotKB Xref RefSeq contains Gallus gallus [taxid:9606] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_refseq.csv","filename":"chicken_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_refseq.stat.csv","filename":"chicken_protein_xref_refseq.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":639,"last_update":"2024-05-21T15:15:18.502378Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000984/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000984/DRAFT","etag":"d10ad4ecee8d1e796b75da248a69f7df25d82af54e66b6062c47a8dc14ff3f11","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Transcript Locus (Ensembl Transcript coordinates)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-16T16:05:08.939322","modified":"2024-06-03T21:04:47.847Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB Gallus gallus [taxid:9606] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_transcriptlocus.csv","filename":"chicken_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_transcriptlocus.stat.csv","filename":"chicken_protein_transcriptlocus.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2024-06-03T21:04:47.847482Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000985/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000985/DRAFT","etag":"d04aa3eef2947bc2bb6840fa11d2d93c4a74ddb1d8d85d4a908ec06137261eed","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref KEGG PATHWAY","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.959744","modified":"2024-06-03T21:05:14.583Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref KEGG PATHWAY contains Gallus gallus [taxid:9606] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_kegg.csv","filename":"chicken_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_kegg.stat.csv","filename":"chicken_protein_xref_kegg.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":412,"last_update":"2024-06-03T21:05:14.583391Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000986/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000986/DRAFT","etag":"dd385b939834de74c44f88194285df43f209c7c87af596bc0f6e813747fc4c00","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.951602","modified":"2024-06-03T21:06:04.721Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Gene Ontology (GO) dataset contains Gallus gallus [taxid:9606] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_go_annotation.csv","filename":"chicken_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_go_annotation.stat.csv","filename":"chicken_protein_go_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":266,"last_update":"2024-06-03T21:06:04.721321Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000987/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000987/DRAFT","etag":"ab77f62af6626912a3aee820d3ccebcdb0ef74cdf6b12d463261485ce249079f","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Reaction Participants (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-07T14:06:11.683031","modified":"2024-05-21T15:09:39.065Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Gallus gallus [taxid:9031] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"database_accession.tsv","uri":"https:/data.glygen.org/ln2downloads/chebi/2024_01_31/database_accession.tsv"}},{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_participants_reactome.csv","filename":"chicken_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_participants_reactome.stat.csv","filename":"chicken_protein_participants_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":375,"last_update":"2024-05-21T15:09:39.065310Z","access_count":15},{"object_id":"https://biocomputeobject.org/GLY_000989/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000989/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:20.996Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Protein Citations dataset contains publication information for Gallus gallus [taxid:9031] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_uniprotkb.csv","filename":"chicken_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_uniprotkb.stat.csv","filename":"chicken_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{},"etag":"69f8cfe98ba7bf41ab6e972da9c05bf9185d889a09a0c09db1cc0545c782ea69"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":419,"last_update":"2024-05-17T11:24:20.996041Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000990/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000990/DRAFT","spec_version":"1.3.0","etag":"cc85fe65ba118bbe24377155b8d16bd82cacea2aa6b8d033c22d5272d4ea41ab","provenance_domain":{"name":"Chicken Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-12T17:35:21","modified":"2024-07-12T17:37:07.299Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","email":"cyruschauyeung@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Gallus gallus [taxid:9031] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_altnames.csv","filename":"chicken_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_altnames.stat.csv","filename":"chicken_protein_altnames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":225,"last_update":"2024-07-12T17:37:07.299441Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_000991/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000991/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:21.070Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken UniProtKB Xref Rhea contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Rhea"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_rhea.csv","filename":"chicken_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_rhea.stat.csv","filename":"chicken_protein_xref_rhea.stat.csv"}}]},"error_domain":{},"etag":"09042a683ac559a2996bc48ae0cc69acbed266f10211d06709d025f48690d635"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":253,"last_update":"2024-05-17T11:24:21.070897Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000992/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000992/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref BRENDA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:21.109Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken UniprotKB Xref BRENDA contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_brenda.csv","filename":"chicken_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_brenda.stat.csv","filename":"chicken_protein_xref_brenda.stat.csv"}}]},"error_domain":{},"etag":"cd7eae084aa21425aaa2404c38165cfc39a1047ada6fff07ee3026dc649289cb"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":480,"last_update":"2024-05-17T11:24:21.109964Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000993/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000993/DRAFT","etag":"ee18878113c52910d31d74686c08f1439e9b985c7d04401599a6a55d15ec1dd9","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.900608","modified":"2024-05-21T14:58:56.407Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Information dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_info_uniprotkb.csv","filename":"chicken_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_info_uniprotkb.stat.csv","filename":"chicken_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":283,"last_update":"2024-05-21T14:58:56.407765Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000994/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000994/DRAFT","etag":"4ef1f1f6d19141ac4b647f704b18d7757b3e2973bc079ef2a5951c6959a82b64","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-03-16T11:26:15.442401","modified":"2024-05-21T14:58:39.113Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Gallus gallus [taxid:9031] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_genenames_uniprotkb.csv","filename":"chicken_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_genenames_uniprotkb.stat.csv","filename":"chicken_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":317,"last_update":"2024-05-21T14:58:39.113936Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000995/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000995/DRAFT","etag":"f2b3aadfc7237e5fb6cd5bc520e2f4a99d89559857a4302da3f94faf19ab1dab","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Function (NCBI Refseq)","version":"v-2.4.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-16T15:35:15.248632","modified":"2024-05-21T14:58:18.581Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Function (NCBI RefSeq) dataset contains biological function annotation of Gallus gallus [taxid:9031] genes from GeneRIF section in the NCBI RefSeq database. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_9606.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2024_02_18/refseq_protein_all_9606.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_function_refseq.csv","filename":"chicken_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_function_refseq.stat.csv","filename":"chicken_protein_function_refseq.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":177,"last_update":"2024-05-21T14:58:18.581112Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_000996/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000996/DRAFT","etag":"cfc745e11536eb9f6d83d641fd30a9b5119e94ffa85e25ccc5260f7d938aba06","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Xref O-GlcNAcAtlas","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:57:54.460Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Chicken Xref O-GlcNAcAtlas dataset contains Gallus gallus (taxid: 9301) UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_oglcnac_atlas.csv","filename":"chicken_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_oglcnac_atlas.stat.csv","filename":"chicken_protein_xref_oglcnac_atlas.stat.csv"}}]}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":142,"last_update":"2024-05-21T14:57:54.460594Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_000997/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000997/DRAFT","spec_version":"1.3.0","etag":"60b378ee028ee6b14c93c4c207bfc8ffaefa40195e2e6b38ff4cb862cd578503","provenance_domain":{"name":"Chicken Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.888176","modified":"2024-07-10T11:18:40.271Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","contribution":["contributedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Information (NCBI RefSeq) dataset contains Gallus gallus [taxid:9301] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein information","protein length","NCBI RefSeq","protein summary"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_refseq.csv"}},{"uri":{"filename":"refseq_protein_all_9606.gpff","uri":"https:/data.glygen.org/ln2downloads/ncbi/refseq/2024_02_18/refseq_protein_all_9606.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_info_refseq.csv","filename":"chicken_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_info_refseq.stat.csv","filename":"chicken_protein_info_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":291,"last_update":"2024-07-10T11:18:40.271530Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_000998/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000998/DRAFT","etag":"fbb652385e4ffbd923dd8ce8336bd3e40655e36d6dbac8b30843cc8f72cd5918","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Proteome Masterlist (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.867420","modified":"2024-06-03T20:32:48.515Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Proteome Masterlist dataset contains Gallus gallus [taxid:9301] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chihcken_protein_masterlist.csv","filename":"chicken_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_masterlist.stat.csv","filename":"chicken_protein_masterlist.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":203,"last_update":"2024-06-03T20:32:48.515771Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_000999/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_000999/DRAFT","etag":"16fc74c044c73ee360f252c186b4d8d0c36a99907930d4e4d6dd22f5469b34a1","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Glycosyltransferases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.870634","modified":"2024-05-21T14:56:49.757Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Hayley Dingerdissen","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"hmhamilt@gwmail.gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosyltransferases dataset contains list of Gallus gallus [taxid:9301] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the chicken proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Gallus gallus (chicken) [9301]\". To retrieve the list of all chicken glycosyltransferases, the full list of chicken proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_glycosyltransferase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/compiled/chicken_protein_glycosyltransferase.csv"}},{"uri":{"filename":"chicken_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_glycosyltransferase.csv","filename":"chicken_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_glycosyltransferase.stat.csv","filename":"chicken_protein_glycosyltransferase.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":2004,"last_update":"2024-05-21T14:56:49.757330Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001000/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001000/DRAFT","etag":"7c3990c2c78973ad11e45949a01df9f305396c4a464df1e3f399455183d114dd","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T15:08:57.534471","modified":"2024-05-21T14:56:11.513Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref PDB contains Gallus gallus [taxid:9301] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_pdb.csv","filename":"chicken_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_pdb.stat.csv","filename":"chicken_protein_xref_pdb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":299,"last_update":"2024-05-21T14:56:11.513597Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001001/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001001/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref Bgee","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:21.457Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken UniProtKB Xref Bgee dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_bgee.csv","filename":"chicken_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_bgee.stat.csv","filename":"chicken_protein_xref_bgee.stat.csv"}}]},"error_domain":{},"etag":"ccc00c90a754bc46b8be0c5b11941ed339f93a5aa5e36939bf6e38fd2e6d4281"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":474,"last_update":"2024-05-17T11:24:21.457744Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001002/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001002/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Names (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:21.493Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Protein Names (NCBI RefSeq) dataset contains Gallus gallus [taxid:9031] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_proteinnames_refseq.csv","filename":"chicken_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_proteinnames_refseq.stat.csv","filename":"chicken_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{},"etag":"b706fa9ecbb829390b75d403b1b3b0a5b2ff5019fde357c8a38c979b262a2aab"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":263,"last_update":"2024-05-17T11:24:21.493830Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001003/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001003/DRAFT","spec_version":"1.3.0","etag":"802b5dce27b453778eff9417bef1acaf77975c8bf6f757552b5092223b7fedab","provenance_domain":{"version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-25T17:47:07","modified":"2024-07-26T12:24:00.536Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Proteoform Glycation Citations (UniProtKB) dataset contains Gallus gallus [taxid:9031] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"]},"parametric_domain":[{"value":""}],"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":280,"last_update":"2024-07-26T12:24:00.536500Z","access_count":11},{"object_id":"https://biocomputeobject.org/GLY_001004/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001004/DRAFT","etag":"dfc4164bdb00ff05e1cdd0f6bd8618c2296e9a451dcce4f9bffedea5257dba46","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T12:05:44.324142","modified":"2024-05-21T14:54:23.305Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref InterPro contains Gallus gallus [taxid:9301] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers.","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_interpro.csv","filename":"chicken_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_interpro.stat.csv","filename":"chicken_protein_xref_interpro.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":375,"last_update":"2024-05-21T14:54:23.305195Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001005/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001005/DRAFT","etag":"6b998d4fa3b5b916d171095861eb2433bf47e7cdca1ace7c55f8f4ebbaa2879b","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.921192","modified":"2024-05-21T14:53:43.709Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Isoform sequences (UniProtKB) dataset contains Gallus gallus [taxid:9301] protein fasta sequences for the chicken isoform accessions from the UniProtKB database."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all chicken isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_allsequences.fasta","filename":"chicken_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_allsequences.stat.csv","filename":"chicken_protein_allsequences.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":181,"last_update":"2024-05-21T14:53:43.709828Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001006/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001006/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref IntAct","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:21.649Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken UniProtKB Xref IntAct dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_intact.csv","filename":"chicken_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_intact.stat.csv","filename":"chicken_protein_xref_intact.stat.csv"}}]},"error_domain":{},"etag":"22e0c0b7d819b3122837d32a3f3eb71ef69a2432e46dce5790cb320b173e754e"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":532,"last_update":"2024-05-17T11:24:21.649538Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001007/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001007/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Site Annotation","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:21.685Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Protein Site Annotation (UniProtKB) dataset contains Gallus gallus [taxid:9031] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_site_annotation_uniprotkb.csv","filename":"chicken_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_site_annotation_uniprotkb.stat.csv","filename":"chicken_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{},"etag":"6861702cca191c77328c9c540b3e3b25e3dfae3a33f719c0e0f83c9b69abbd38"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":314,"last_update":"2024-05-17T11:24:21.685556Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001008/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001008/DRAFT","etag":"7a41554f7d55a8a53493429305ad80f64ba5494319fa58011dd7d38e1161f086","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Submitted Names (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-03-15T13:38:29.540245","modified":"2024-05-21T14:18:23.180Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Gallus gallus [taxid:9031] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_submittednames.csv","filename":"chicken_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_submittednames.stat.csv","filename":"chicken_protein_submittednames.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":511,"last_update":"2024-05-21T14:18:23.180029Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001009/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001009/DRAFT","spec_version":"1.3.0","etag":"87fe00826318a4f296aa7e6cf78f67b120653f0c068ff6f663296778de9b130d","provenance_domain":{"name":"Chicken Glycosylation Sites (RCSB PDB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.909814","modified":"2026-08-19T10:00:18.597Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jasmine Young","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"jasmine@rcsb.rutgers.edu"},{"name":"Chenghua Shao","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"chenghua@rcsb.rutgers.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosylation Sites (RCSB PDB) dataset contains Gallus gallus [taxid:9031] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"input_list":[]}],"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt"}},{"uri":{"filename":"N-linked-ARG-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_glycosylation_sites_pdb.csv","filename":"chicken_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_glycosylation_sites_pdb.stat.csv","filename":"chicken_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":511,"last_update":"2026-08-19T10:00:18.597065Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001010/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001010/DRAFT","etag":"c86a26191deb23f76712ce89b75b9b5238ae84381353b9ff4412eadf672a2248","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Citations (RefSeq)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:38.983152","modified":"2024-05-21T14:12:55.301Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Citations (RefSeq) datasets contains Gallus gallus [taxid:9031] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/compiled/chicken_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"chicken_protein_function_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_function_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_citations_refseq.csv","filename":"chicken_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_citations_refseq.stat.csv","filename":"chicken_protein_citations_refseq.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":315,"last_update":"2024-05-21T14:12:55.301181Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001011/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001011/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Proteoform O-GlcNAc Glycosylation Citations (MCW)","version":"v-x.x.x","license":"httpss://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:21.835Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset chicken O-GlcNAc Glycosylation Sites (MCW) https://data.glygen.org/GLY_000959, contributed by Stephanie Olivier's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed","MCW","Glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"chicken_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"chicken_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{},"etag":"1ffbd4c18a314d196e80260c79ae3ff8d4ccdf5f5ab84af224f0ab4a08efbe4e"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":238,"last_update":"2024-05-17T11:24:21.835134Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001012/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001012/DRAFT","etag":"e4ab0bae7bb881ffa7b5a9c0a29b18051bc07e55719c1b65fa5aed8b688f26ba","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref CDD","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T12:09:02.680538","modified":"2024-05-21T14:14:43.331Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref CDD contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you are using this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_cdd.csv","filename":"chicken_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_cdd.stat.csv","filename":"chicken_protein_xref_cdd.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":431,"last_update":"2024-05-21T14:14:43.331457Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001013/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001013/DRAFT","etag":"731fe65abc3c3696a343d61f295c340c076ecbba66c8d2e0b9f00097fd950531","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Recommended Names (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.956673","modified":"2024-05-21T13:51:03.948Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Gallus gallus [taxid:9031] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_recnames.csv","filename":"chicken_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_recnames.stat.csv","filename":"chicken_protein_recnames.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":227,"last_update":"2024-05-21T13:51:03.948040Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001014/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001014/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Signal Peptide","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-03T22:38:19.443Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Protein Signal Peptide dataset contains Gallus gallus [taxid:9031] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. Signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. ","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_annotation.csv","filename":"chicken_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_peptidesequences.fasta","filename":"chicken_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_cleavedsequences.fasta","filename":"chicken_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_fullsequences.fasta","filename":"chicken_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_annotation.stat.csv","filename":"chicken_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_peptidesequences.stat.csv","filename":"chicken_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_cleavedsequences.stat.csv","filename":"chicken_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_signalp_fullsequences.stat.csv","filename":"chicken_protein_signalp_fullsequences.stat.csv"}}]},"etag":"12140acf271a41461886b3253573b5ff2c373721af8c7124ee03af0da6d5f307"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":686,"last_update":"2024-06-03T22:38:19.443940Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001015/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001015/DRAFT","etag":"fc8ffa26b0845cc826fc2c559c4036d4c210cab3b1db1f0861432be56273f4e0","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Proteoform Glycosylation Citations (UniProtKB)","version":"v-2.5.1","created":"2021-06-03T16:32:02.053252","modified":"2024-05-29T19:23:13.269Z","contributors":[{"name":"Jeet Vora","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Proteoform Glycosylation Citations (UniProtKB) dataset contains Gallus gallus [taxid:9031] citation details of the publications present in the dataset Chicken Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000965)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_glycosylation_sites_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"chicken_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"chicken_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":240,"last_update":"2024-05-29T19:23:13.269163Z","access_count":15},{"object_id":"https://biocomputeobject.org/GLY_001016/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001016/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Human Glycosylation Diabetes Glycomics Study Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-04T13:25:08.357Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Olga Gornik","affiliation":"University of Zagreb","contribution":["contributedBy"],"email":"ogornik@pharma.hr"},{"name":"Nadja Rudman","affiliation":"University of Zagreb","email":"najda.rudman@gmail.com","contribution":["contributedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset contains publication information of the PMIDs present in the Human Glycosylation Sites Diabetes Glycomics Study dataset (https://data.glygen.org/GLY_000960)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Diabetes glycomic study citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Publications","Citations","PubMed","glycomics","Diabetes"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_diabetes_glycomic.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_diabetes_glycomic.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_diabetes_glycomic.csv","filename":"human_proteoform_citations_glycosylation_sites_diabetes_glycomic.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_diabetes_glycomic.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_diabetes_glycomic.stat.csv"}}]},"etag":"40498bb0f1d9191417364a9b6c32d8252084050887939f4a4f42ac67165ee9f2"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":169,"last_update":"2024-06-04T13:25:08.357950Z","access_count":10},{"object_id":"https://biocomputeobject.org/GLY_001018/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001018/DRAFT","spec_version":"1.3.0","etag":"08850c57771b22b8dcf70c7371f60ad7f18d37df7676c48d097159b2aff17108","provenance_domain":{"name":"Chicken Gene Symbols (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-12T17:02:40","modified":"2024-07-12T17:05:09.764Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","email":"cyruschauyeung@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Gene Symbols (NCBI RefSeq) dataset contains Gallus gallus [taxid:9031] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_genenames_refseq.csv","filename":"chicken_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_genenames_refseq.stat.csv","filename":"chicken_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":251,"last_update":"2024-07-12T17:05:09.764463Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001019/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001019/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Human Glycosylation Citations (EMBL)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:22.148Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Clement Potel","affiliation":"EMBL","email":"clement.potel@embl.de","contribution":["contributedBy"]},{"name":"Mira Burtscher","affiliation":"EMBL","email":"mira.burtscher@embl.de","contribution":["contributedBy"]},{"name":"Martin Garrido","affiliation":"EMBL","email":"martin.garrido@embl.de","contribution":["contributedBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Citations (EMBL) dataset contains publication information of the PMIDs present in the Human Glycosylation Sites (EMBL) dataset (https://data.glygen.org/GLY_000888)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Publications","Citations","PubMed","glycosylation","EMBL"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_citations_glycosylation_sites_embl.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_embl.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_embl.csv","filename":"human_proteoform_citations_glycosylation_sites_embl.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_embl.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_embl.stat.csv"}}]},"etag":"d9e11b0eda79a2796a809d623c474c859cf4f8f3013803754b1e9dee5bb91e78"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":188,"last_update":"2024-05-17T11:24:22.148405Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001020/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001020/DRAFT","etag":"d85b62814096a7a73bed7c3ac988085b7388873bd92cf1cc19467860e611c2e9","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref NCBI Gene","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T12:11:47.098435","modified":"2024-05-21T13:47:38.033Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref NCBI Gene dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_geneid.csv","filename":"chicken_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_geneid.stat.csv","filename":"chicken_protein_xref_geneid.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":508,"last_update":"2024-05-21T13:47:38.033667Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001021/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001021/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Glycosylation Citations (EMBL)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:22.227Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Clement Potel","affiliation":"EMBL","email":"clement.potel@embl.de","contribution":["contributedBy"]},{"name":"Mira Burtscher","affiliation":"EMBL","email":"mira.burtscher@embl.de","contribution":["contributedBy"]},{"name":"Martin Garrido","affiliation":"EMBL","email":"martin.garrido@embl.de","contribution":["contributedBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Citations (EMBL) dataset contains publication information of the PMIDs present in the Mouse Glycosylation Sites (EMBL) dataset (https://data.glygen.org/GLY_000889)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Publications","Citations","PubMed","glycosylation","EMBL"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_citations_glycosylation_sites_embl.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_glycosylation_sites_embl.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_glycosylation_sites_embl.csv","filename":"mouse_proteoform_citations_glycosylation_sites_embl.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_glycosylation_sites_embl.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_embl.stat.csv"}}]},"etag":"41bac2ae1e00907272fa3701d7f20219d0a5211d89f9763a91918a2c365769ec"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":188,"last_update":"2024-05-17T11:24:22.227317Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001022/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001022/DRAFT","etag":"98da0093e4a0877c860b24f3d2bef348dc9250b35a7720c098d4db361e8718eb","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Reactions (Reactome)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-30T15:08:38.029791","modified":"2024-05-21T13:48:30.931Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Reactions (Reactome) dataset contains reactions information for pathways for Gallus gallus [taxid:9031] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_reactions_reactome.csv","filename":"chicken_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_reactions_reactome.stat.csv","filename":"chicken_protein_reactions_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-21T13:48:30.931949Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001023/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001023/DRAFT","etag":"c96b6efe4e532d3ff19cc233383fb4213453083d48b3c28c7494ec647da4fddb","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Phosphorylation Sites (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-06-14T14:54:26.195339","modified":"2024-05-21T13:46:53.289Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Phosphorylation Sites (UniProtKB) dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_19/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"chicken_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"chicken_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-05-21T13:46:53.289233Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001024/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001024/DRAFT","etag":"34db16717f8149114971c3bb9f3e7f927d333697ecc79b6e86b1887755696d79","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Glycohydrolases","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.892318","modified":"2024-05-21T14:21:00.920Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycohydrolases dataset contains a list of Gallus gallus [taxid:9301] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_glycohydrolase.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/compiled/chicken_protein_glycohydrolase.csv"}},{"uri":{"filename":"chicken_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_glycohydrolase.csv","filename":"chicken_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_glycohydrolase.stat.csv","filename":"chicken_protein_glycohydrolase.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":289,"last_update":"2024-05-21T14:21:00.920252Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_001025/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001025/DRAFT","etag":"c9c38e9a08edaf922f492467573044fba82cfe8ee65ebb365c0e67887de72ad8","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Reactions (Rhea)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-06-03T17:38:21.320871","modified":"2024-05-23T16:52:58.428Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Reactions (Rhea) dataset contains reactions information for pathways for Gallus gallus [taxid:9031] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","reactions","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Rhea reaction annotations triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_reactions_rhea.csv","filename":"chicken_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_reactions_rhea.stat.csv","filename":"chicken_protein_reactions_rhea.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"jingyue.wu","authorized_users":null,"state":"DRAFT","score":335,"last_update":"2024-05-23T16:52:58.428053Z","access_count":21},{"object_id":"https://biocomputeobject.org/GLY_001026/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001026/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Proteoform Phosphorylation Citations (iPTMnet)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T11:24:22.427Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Chicken Proteoform Citations (iPTMNet) contains Gallus gallus [taxid:9031] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","iPTMnet","PubMed","Phosphorylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","input_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"chicken_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"chicken_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{},"etag":"21cc79c0689359b06553b6d5a966735034596546b90c1a90a7e49a20a46c5216"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":347,"last_update":"2024-05-17T11:24:22.427783Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001027/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001027/DRAFT","spec_version":"1.3.0","etag":"d1196d26eb82f6668cd6a83a9d7ab1e03ac791253ab2f39c87849961209d116c","provenance_domain":{"name":"Human Glycosylation Citations ccRCC (PDC)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-23T00:41:07.742Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset contains publication information of the PMIDs present in the Human Glycosylation Sites ccRCC (PDC) dataset (https://data.glygen.org/GLY_000961)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}],"keywords":["Publications","Citations","PubMed","N-linked glycosylation","glycoproteomics","clear cell renal cell carcinoma","PDC"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_pdc_ccrcc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_pdc_ccrcc.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_pdc_ccrcc.csv","filename":"human_proteoform_citations_glycosylation_sites_pdc_ccrcc.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_pdc_ccrcc.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_pdc_ccrcc.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":156,"last_update":"2024-07-23T00:41:07.742962Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001028/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001028/DRAFT","etag":"ce26c2e81f07a715a2de49db35981131df240a4456ec9df44871802b4a20e9c2","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Citations (Reactome)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:50:00.047Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Reactions (Reactome) dataset contains reactions information for pathways for Gallus gallus [taxid:9031] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/compiled/chicken_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"chicken_protein_reactions_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_reactions_reactome.csv"}},{"uri":{"filename":"chicken_protein_xref_reactome.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_reactome.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_citations_reactome.csv","filename":"chicken_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_citations_reactome.stat.csv","filename":"chicken_protein_citations_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-05-21T14:50:00.047743Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001029/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001029/DRAFT","etag":"d4b81e0d4e34f32608e50e09d35e92eaf5c76d8dd2150a492ad4b8d5b1cd0418","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Enzyme Annotation (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:49:34.499Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Enzyme Annotation (UniProtKB) dataset contains Gallus gallus [taxid:9031] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_enzyme_annotation_uniprotkb.csv","filename":"chicken_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"chicken_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":320,"last_update":"2024-05-21T14:49:34.499749Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001030/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001030/DRAFT","etag":"584ce49ba3a78476ceff155eafd79d87084542e5c20741b2903abdf730a8be88","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein PTM Annotation (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:49:08.136Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein PTM Annotation (UniProtKB) dataset contains Gallus gallus [taxid:9031] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_ptm_annotation_uniprotkb.csv","filename":"chicken_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_ptm_annotation_uniprotkb.stat.csv","filename":"chicken_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-05-21T14:49:08.136488Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001031/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001031/DRAFT","etag":"89eb09ef3c7899c06673a772f588636bdecfaa318539ebb519246f85721f3945","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref Pfam","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:48:42.001Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref Pfam contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_pfam.csv","filename":"chicken_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/chicken_protein_xref_pfam.stat.csv","filename":"chicken_protein_xref_pfam.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":391,"last_update":"2024-05-21T14:48:42.001306Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001032/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001032/DRAFT","etag":"133875f3743e6dcf4e6df91f78927228e79b30093979fb50d44e3ac6380ada3a","spec_version":"1.3.0","provenance_domain":{"name":"Chicken O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:29:25.540Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Chicken O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000962, contributed by Jungfeng Ma's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"chicken_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"chicken_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":255,"last_update":"2024-05-21T14:29:25.540717Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001033/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001033/DRAFT","etag":"b6ed6706309d6d7a4b96cff34f6ac90c72619f884032f34e3f356622508fca93","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Phosphorylation Sites (iPTMNet)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:44:44.886Z","contributors":[{"name":"Jeet Vora","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Phosphorylation Sites (iPTMNet) dataset contains Gallus gallus [taxid:9031] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"https:/data.glygen.org/ln2downloads/iptmnet/2024_01_31/ptm.txt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_phosphorylation_sites_iptmnet.csv","filename":"chicken_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"chicken_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":296,"last_update":"2024-05-21T14:44:44.886205Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001034/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001034/DRAFT","etag":"b4f35b9504df08ba32ffc1f9d16f0caeb7ebb07cb7c43e7e2a9ff0ed782e59ce","spec_version":"1.3.0","provenance_domain":{"name":"Chicken EBI-UniProtKB NT file","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:43:29.628Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken EBI-UniProtKB NT file contains proteome data for Gallus gallus [taxid:9031] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_ntdata.nt","filename":"chicken_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_ntdata.stat.csv","filename":"chicken_protein_ntdata.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":273,"last_update":"2024-05-21T14:43:29.628248Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001035/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001035/DRAFT","etag":"0197527387b273545a909fafbf26662cdca142a81fb34abff5a74d2af7fd9fea","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Function (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:42:46.406Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Function (UniProtKB) dataset contains biological function annotation for Gallus gallus [taxid:9031] protein accessions from the UniProtKB database.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_blacklisted_pmids_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/compiled/chicken_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_19/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_function_uniprotkb.csv","filename":"chicken_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_function_uniprotkb.stat.csv","filename":"chicken_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":261,"last_update":"2024-05-21T14:42:46.406039Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001036/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001036/DRAFT","etag":"4763180f135ca426215a4555db82437fc597d6c742038484a792317f270b0759","spec_version":"1.3.0","provenance_domain":{"version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-06-04T14:42:37.422Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"George Washington University","contribution":["createdBy"],"email":"rykahsay@email.gwu.edu"},{"name":"Vijay Shanker","affiliation":"University of Delaware","contribution":["contributedBy"],"email":"vijay@udel.edu"},{"name":"Karen Ross","affiliation":"Georgetown University","contribution":["contributedBy","curatedBy"],"email":"ker25@georgetown.edu"},{"name":"Catherine Hayes","affiliation":"GlyConnect","contribution":["curatedBy"],"email":"hayescat@gmail.com"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["List of Gallus gallus [taxid:9031] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining","Manual QC"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"dicty_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/dicty_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"dicty_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"fruitfly_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_gptwiki.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_harvard.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_o_gluc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"human_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_pdb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"}},{"uri":{"filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_literature.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"yeast_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/yeast_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"filename":"yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv"}},{"uri":{"filename":"yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"uri":{"filename":"yeast_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/yeast_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt"}}],"output_subdomain":[{"mediatype":"csv"}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":572,"last_update":"2024-06-04T14:42:37.422720Z","access_count":9},{"object_id":"https://biocomputeobject.org/GLY_001037/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001037/DRAFT","etag":"10a65e92ddbdfdc74563c3bced6702878e5d2573ce9c04a8a2bafde7d7a515f6","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:36:37.596Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref (UniProtKB) dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_uniprotkb.csv","filename":"chicken_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_uniprotkb.stat.csv","filename":"chicken_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":257,"last_update":"2024-05-21T14:36:37.596235Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001038/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001038/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Reaction Participants (Rhea)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T13:54:15.691Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for chicken [taxid:9031] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_participants_rhea.csv","filename":"chicken_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_participants_rhea.stat.csv","filename":"chicken_protein_participants_rhea.stat.csv"}}]},"error_domain":{},"etag":"dc4209b634b72502c8bf0cb12ad79942f9dfa4e3a38d6bd1075f3fcce5065180"},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2024-05-21T13:54:15.691984Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001039/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001039/DRAFT","etag":"5997676f7fe0e3c3aabd3b6e42d271a6a651922df872af1c8edff75ff16a8182","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Protein Sequence Info (UniProtKB)","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:32:29.580Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Protein Sequence Info (UniProtKB) dataset contains Gallus gallus [taxid:9031] UniProtKB protein fasta sequence information that includes sequence version and fasta header.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB sequence for all chicken isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_sequenceinfo.csv","filename":"chicken_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_sequenceinfo.stat.csv","filename":"chicken_protein_sequenceinfo.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":275,"last_update":"2024-05-21T14:32:29.580150Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001040/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001040/DRAFT","etag":"ece5b3d49ae7ed53898f65bfe67dd22cbddff5aff222a045cca89527112f0bd2","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref CAZy","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:32:00.342Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniprotKB Xref CAZy contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_cazy.csv","filename":"chicken_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_cazy.stat.csv","filename":"chicken_protein_xref_cazy.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":469,"last_update":"2024-05-21T14:32:00.342510Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001041/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001041/DRAFT","etag":"0eddb7ba46328bf8dcfb87ed6a8f367282149ab23c082fa75c78e1c88d9f6d45","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref Reactome","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:31:33.720Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref Reactome contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_reactome.csv","filename":"chicken_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_reactome.stat.csv","filename":"chicken_protein_xref_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":350,"last_update":"2024-05-21T14:31:33.720555Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001042/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001042/DRAFT","etag":"947dca24a412646910c454c2b2646576a1ef48642fc404e5ab3a2b8656aae497","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref ChEMBL","version":"v-2.5.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T14:31:10.376Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniprotKB Xref ChEMBL contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_chembl.csv","filename":"chicken_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_chembl.stat.csv","filename":"chicken_protein_xref_chembl.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-05-21T14:31:10.376415Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001043/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001043/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Yeast UniProtKB Xref Reactome","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-17T20:02:31.344Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{},"parametric_domain":[{"value":""}],"usability_domain":["The Yeast UniProtKB Xref Reactome contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_reactome.csv","filename":"yeast_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_reactome.stat.csv","filename":"yeast_protein_xref_reactome.stat.csv"}}]},"etag":"73e23d2c4d41cffc01ba328ce0d5220fc43bddf3ce8fd1f07b57dbe8c40403ae"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":367,"last_update":"2024-05-17T20:02:31.344211Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001044/DRAFT","contents":{"provenance_domain":{"name":"Yeast Pathways (Reactome)","version":"v-x.x.x","created":"","modified":"","contributors":[{"affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Yeast Pathways (Reactome) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","Reactome is an open-source, open access, manually curated and peer-reviewed pathway database."],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Reactome Pathways for UniProtKB canonical accessions from the triplestore containing triples from nt file and extracts the data as a csv dataset.","version":"","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_pathways_reactome.csv","filename":"yeast_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_pathways_reactome.stat.csv","filename":"yeast_protein_pathways_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"object_id":"https://biocomputeobject.org/GLY_001044/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":""},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-05-17T20:06:54.018222Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001045/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001045/DRAFT","spec_version":"1.3.0","etag":"14acaab94c2d309f374f73e1f05c11032ad4a932df71b4684465d5e353030eb3","provenance_domain":{"name":"Human Diabetes Glycomics (ML Ready)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-23T00:43:32","modified":"2024-07-23T00:50:48.524Z","contributors":[{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Olga Gornik","affiliation":"University of Zagreb","email":"ogornik@pharma.hr","contribution":["contributedBy"]},{"name":"Nadja Rudman","affiliation":"University of Zagreb","email":"najda.rudman@gmail.com","contribution":["contributedBy"]}]},"usability_domain":["The Human Diabetes Glycomics (ML Ready) dataset contains abundance information on the plasma N-glycome of individuals participating in the FinRisk study and can be used to predict risk of incident diabetes within a 10 year follow up period. Baseline samples were analyzed from 37 individuals who developed type 2 diabetes within 10 years and 37 sex and age matched individuals who remained normoglycaemic. HILIC-UPLC chromatograms were separated into 46 peaks, and were assigned to the most abundant glycan structures in each peak (see Fig 1 of Ref 1). The data was provided by Dr. Olga Gornik, Faculty of Pharmacy and Biochemistry, University of Zagreb and cleaned by the GlyGen team to make ready for machine learning algorithms. If you use this dataset please provide proper attribution to the source publication [1] and GlyGen.","References: 1) Keser T, Gornik I, Vučković F, Selak N, Pavić T, Lukić E, Gudelj I, Gašparović H, Biočina B, Tilin T, Wennerström A, Männistö S, Salomaa V, Havulinna A, Wang W, Wilson JF, Chaturvedi N, Perola M, Campbell H, Lauc G, Gornik O. Increased plasma N-glycome complexity is associated with higher risk of type 2 diabetes. Diabetologia. 2017;60(12):2352-2360. doi:10.1007/s00125-017-4426-9. PMID:28905229.","Content: This dataset consists of 74 instances with 51 columns. A description of the headers follows. Sample: The unique identifier of the patient. Cohort: The study cohort. BL_AGE: Age at baseline. DIAB_AGE: Age at follow up. GP*_*: Glycan peak number and GlyTouCan accession mapped to each peak based on the glycan topology.","Processing scripts, exploratory data analysis and models trained on this dataset can be found at https://github.com/glygener/glygen-machine-learning/tree/main/diabetes_glycomic"],"description_domain":{"keywords":["N-glycome","Publications","Citations","PubMed","Diabetes","Machine Learning","Data Science","Artificial Intelligence","AI"],"pipeline_steps":[{"step_number":1,"input_list":[{"filename":"HG_FinnRisk.txt","uri":"https://data.glygen.org/ln2downloads/zagreb/current/HG_FinnRisk.txt"},{"filename":"gtc_headers.csv","uri":"https://data.glygen.org/ln2data/releases/data/v-2.5.1/misc/gtc_headers.csv"}],"name":"https://github.com/glygener/glygen-machine-learning/blob/main/diabetes_glycomic/diabetes_preprocessing.py","description":"Processing script that formats the data, drops redundant columns and derived traits, and maps GlyTouCan accessions to peak numbers.","output_list":[{"filename":"human_proteoform_ml_ready_diabetes_glycomic.csv","uri":"https://data.glygen.org/ln2data/releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_diabetes_glycomic.csv"}]}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"uri":"https://data.glygen.org/ln2downloads/zagreb/current/HG_FinnRisk.txt","filename":"HG_FinnRisk.txt"}},{"uri":{"uri":"https://data.glygen.org/ln2data/releases/data/v-2.5.1/misc/gtc_headers.csv","filename":"gtc_headers.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_ml_ready_diabetes_glycomic.csv","filename":"human_proteoform_ml_ready_diabetes_glycomic.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_ml_ready_diabetes_glycomic.stat.csv","filename":"human_proteoform_ml_ready_diabetes_glycomic.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-machine-learning/blob/main/diabetes_glycomic/diabetes_preprocessing.py","filename":"diabetes_preprocessing.ipynb"}}],"software_prerequisites":[{"name":"Python","version":"3.11.5","uri":{"uri":"https://www.python.org/download/releases/3.11.5/"}},{"name":"Pandas","version":"1.5.3","uri":{"uri":"https://pandas.pydata.org/pandas-docs/version/1.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Diabetes glycomic study","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Machine Learning","category_name":"usability"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":1745,"last_update":"2024-07-23T00:50:48.524769Z","access_count":18},{"object_id":"https://biocomputeobject.org/GLY_001046/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001046/DRAFT","spec_version":"1.3.0","etag":"67c1fbcf4529de6c7762221efff5eeb7c4f0b78a362d5b3ee408031cda502cce","provenance_domain":{"name":"Human ccRCC Glycoproteomics (ML Ready)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-06-28T06:27:01","modified":"2024-07-23T00:48:08.852Z","contributors":[{"name":"Karina Martinez","affiliation":"The George Washington University","email":"karinamartinez@gwu.edu","contribution":["createdBy","curatedBy"]}]},"usability_domain":["The Human Glycosylation Sites (PDC) dataset contains intact glycopeptide abundances, biospecimen and clinical metadata from Homo sapiens (taxid:9606) clear cell renal cell carcinoma (ccRCC) tumor and normal adjacent tissues collected by the CPTAC program and can be used to stratify risk groups of ccRCC patients. The data was retrieved from the Proteomic Data Commons (PDC) and can be accessed at https://proteomic.datacommons.cancer.gov/pdc/study/PDC000471. The abundances and clinical features were combined and cleaned by the GlyGen team to make ready for machine learning algorithms. If you use this dataset please provide proper attribution to the source publication [1], PDC and GlyGen.","References: 1) Lih TM, Cho KC, Schnaubelt M, Hu Y, Zhang H. Integrated glycoproteomic characterization of clear cell renal cell carcinoma. Cell Rep. 2023 May 30;42(5):112409. doi: 10.1016/j.celrep.2023.112409. Epub 2023 Apr 18. PMID: 37074911; PMCID: PMC10247542.","Content: This dataset consists of 183 instances with 11103 columns. Columns 1-10815 contain glycopeptide abundances with missing values imputed for intact glycopeptides quantified in >50% of the samples using DreamAI (https://github.com/WangLab-MSSM/DreamAI). A description of key biospecimen and clinical headers follows. tissue type: Normal or Tumor. cause of death: Cancer related, Infection, Unknown. days to death: Days to death after resection. vital status: Alive or Dead. last known disease status: With tumor, Tumor free or Unknown tumor status. progression or recurrence: Yes, No or Not Reported. disease response: PD-Progressive Disease or CR-Complete Response. ","Processing scripts, exploratory data analysis and models trained on this dataset can be found at https://github.com/glygener/glygen-machine-learning/tree/main/pdc_ccrcc"],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[{"filename":"ccRCC_TMT_intact glycopeptide_abundance_MD-MAD_50percentQuant_imputed.tsv","uri":"https://data.glygen.org/ln2downloads/pdc/current/ccRCC_TMT_intact%20glycopeptide_abundance_MD-MAD_50percentQuant_imputed.tsv"},{"filename":"PDC_study_biospecimen_09182023_104440.tsv","uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_biospecimen_09182023_104440.tsv"},{"filename":"PDC_study_clinical_09182023_105327.tsv","uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_clinical_09182023_105327.tsv"},{"filename":"PDC_study_clinical_exposure_09182023_105327.tsv","uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_clinical_exposure_09182023_105327.tsv"},{"filename":"PDC_study_clinical_followup_09182023_105327.tsv","uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_clinical_followup_09182023_105327.tsv"}],"name":"https://github.com/glygener/glygen-machine-learning/blob/main/pdc_ccrcc/ccrcc_preprocessing.py","description":"Processing script that formats the data and combines abundance, biospecimen and clinical data into one file.","output_list":[{"filename":"human_proteoform_ml_ready_pdc_ccrcc.csv","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_ml_ready_pdc_ccrcc.csv"}]}],"keywords":["N-linked glycosylation","glycoproteomics","clear cell renal cell carcinoma","PDC","Machine Learning","Data Science","Artificial Intelligence","AI"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"MAD_50percentQuant_imputed.tsv","uri":"https://data.glygen.org/ln2downloads/pdc/current/ccRCC_TMT_intact%20glycopeptide_abundance_MD-MAD_50percentQuant_imputed.tsv"}},{"uri":{"uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_biospecimen_09182023_104440.tsv","filename":"PDC_study_biospecimen_09182023_104440.tsv"}},{"uri":{"uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_clinical_09182023_105327.tsv","filename":"PDC_study_clinical_09182023_105327.tsv"}},{"uri":{"uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_clinical_exposure_09182023_105327.tsv","filename":"PDC_study_clinical_exposure_09182023_105327.tsv"}},{"uri":{"uri":"https://data.glygen.org/ln2downloads/pdc/current/PDC_study_clinical_followup_09182023_105327.tsv","filename":"PDC_study_clinical_followup_09182023_105327.tsv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_ml_ready_pdc_ccrcc.csv","filename":"human_proteoform_ml_ready_pdc_ccrcc.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_ml_ready_pdc_ccrcc.stat.csv","filename":"human_proteoform_ml_ready_pdc_ccrcc.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"ccrcc_preprocessing.py","uri":"https://github.com/glygener/glygen-machine-learning/blob/main/pdc_ccrcc/ccrcc_preprocessing.py"}}],"software_prerequisites":[{"name":"Python","version":"3.11.5","uri":{"uri":"https://www.python.org/download/releases/3.11.5/"}},{"name":"Pandas","version":"1.5.3","uri":{"uri":"https://pandas.pydata.org/pandas-docs/version/1.5/"}},{"name":"Numpy","version":"1.26.3","uri":{"uri":"https://numpy.org/doc/1.26/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites ccRCC (PDC)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Machine Learning","category_name":"usability"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":1797,"last_update":"2024-07-23T00:48:08.852972Z","access_count":14},{"object_id":"https://biocomputeobject.org/GLY_001047/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001047/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"provenance_domain":{"name":"Rat Glycan Interaction Data (MatrixDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-05-21T16:19:48.659Z","contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLY_000244)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"usability_domain":["The Rat Glycan Interaction Data (MatrixDB) dataset contains interaction data between Rattus norvegicus [taxid:10116] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_matrixdb.stat.csv","filename":"rat_protein_matrixdb.stat.csv"}}]},"error_domain":{},"etag":"362cfd65f6355b269741f2b9e991d328cabbf8f2b46e99caac5b0df945bed6ad"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":309,"last_update":"2024-05-21T16:19:48.659341Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001048/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001048/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Rat Glycan Interaction Data Citations (MatrixDB)","version":"v-x.x.x","modified":"2024-05-21T16:21:21.433Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Sylvie Ricard-Blum","affiliation":"MatrixDB","contribution":["contributedBy"],"email":"sylvie.ricard-blum@univ-lyon1.fr"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Rat Glycan Interaction Data Citations (MatrixDB) dataset contains details of the publication present in the Rat Glycan Interaction Data (MatrixDB) dataset (https://data.glygen.org/GLY_001047)."],"description_domain":{"keywords":["MatrixDB","Glycan Interaction","Publications","Citations","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_matrixdb.csv","filename":"rat_protein_citations_matrixdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_matrixdb.stat.csv","filename":"rat_protein_citations_matrixdb.stat.csv"}}]},"parametric_domain":[{"value":""}],"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycan Interaction Data Citations (MatrixDB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"etag":"05793b537b34d52c8d930917cdab6334b120abf45402b6da162fb7b5742ed7ec"},"prefix":"GLY","owner":"karinamartinez96","authorized_users":null,"state":"DRAFT","score":196,"last_update":"2024-05-21T16:21:21.433636Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001049/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001049/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a6f589ad8b88ee1bd0f141c1cce7c2ec35dd913bae0731943622fdd0702bf67d","provenance_domain":{"name":"Arabidopsis O-GlcNAc Glycosylation Sites (MCW)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-06-25T18:12:53","modified":"2024-06-25T21:09:55.213Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","email":"solivier@mcw.edu","contribution":["createdBy"]},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","email":"rberendt@mcw.edu","contribution":["createdBy"]},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","email":"rberendt@mcw.edu","contribution":["createdBy"]},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","email":"massman@mcw.edu","contribution":["createdBy"]},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","email":"ldanner@mcw.edu","contribution":["createdBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University ","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University ","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","email":"cyruschauyeung@gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Arabidopsis O-GlcNAc Glycosylation Sites (MCW) contains Arabidopsis thaliana (taxid:3702) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Arabidopsis O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021)","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s arabidopsis protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to arabidopsis species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding arabidopsis UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":2503,"last_update":"2024-06-25T21:09:55.213506Z","access_count":18},{"object_id":"https://biocomputeobject.org/GLY_001050/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001050/DRAFT","spec_version":"1.3.0","etag":"ee1d80857cd0bc71035f5b9af118ada032580548a271ea99b2c5e114dd326d67","provenance_domain":{"name":"Arabidopsis O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-06-25T21:16:52.034Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Arabidopsis thaliana (taxid:3702) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":["O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":297,"last_update":"2024-06-25T21:16:52.034345Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001051/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001051/DRAFT","spec_version":"1.3.0","etag":"82292ea44cc167e0cb5914a3133295b24e2e546f563558532fa53c7b8d5f3538","provenance_domain":{"name":"Human blood platelet Glycosylation Sites","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T12:27:42","modified":"2024-08-06T13:58:24.773Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy","curatedBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human blood platelet Glycosylation Sites dataset contains glycosylation sites of thrombin-treated platelet proteins from Homo sapiens (taxid:9606). ESI-MS/MS and unbiased post-translational modification analysis of high-dose thrombin-treated releasate proteins, revealed O-glycosylation as a common modification of the secreted proteins and diverse O-glycan structures. A new form of domain-specific O-fucosylation was also detected within the elastin microfibril interface (EMI) domain of MMRN1, and was found to be important for it's secretion. The raw MS data can be found in the PRIDE repository under ID PXD045535.","The dataset was generated collaboratively by labs at several institutes: The Heart Research Institute, Central Clinical School, and Charles Perkins Centre, at the University of Sydney in Australia, the Department of Biochemistry and Molecular Biology at the University of Georgia in the USA, and the Institute for Glyco-Core Research at the Nagoya University in Japan."],"description_domain":{"keywords":["o-glycosylation","o-fucosylation","o-mannosylation","o-linked","platelet","c-linked"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-Gluc modified residue against UniProtKB Canonical sequences."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_platelet.csv","filename":"human_proteoform_glycosylation_sites_platelet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_platelet.stat.csv","filename":"human_proteoform_glycosylation_sites_platelet.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glucosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":991,"last_update":"2024-08-06T13:58:24.773323Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_001052/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001052/DRAFT","spec_version":"1.3.0","etag":"4539cb1e0c226c29c4b8e82e8ee83951f5ae23f29ad659b8544dacc2533d7295","provenance_domain":{"name":"Arabidopsis Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.921192","modified":"2024-07-08T10:47:46.475Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Isoform sequences (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] protein fasta sequences for the arabidopsis isoform accessions from the UniProtKB database."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all chicken isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}],"keywords":["protein isoform sequences","fasta","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_allsequences.fasta","filename":"arabidopsis_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_allsequences.stat.csv","filename":"arabidopsis_protein_allsequences.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":196,"last_update":"2024-07-08T10:47:46.475096Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001053/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001053/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-08T11:48:54","modified":"2024-07-08T11:51:42.650Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Arabidopsis Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Arabidopsis thaliana [taxid:3702] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_altnames.csv","filename":"arabidopsis_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_altnames.stat.csv","filename":"arabidopsis_protein_altnames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"691b0c59ecbd02082c8979a64bc7a35e4cd7068a06df406e91af0dc64a980cde"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":236,"last_update":"2024-07-08T11:51:42.650277Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001054/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001054/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Binary Interactions (IntAct)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-08T12:02:42","modified":"2024-07-08T12:05:36.480Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Binary Interaction (IntAct) dataset contains Arabidopsis thaliana [taxid:3702] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc.  If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","input_list":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}],"keywords":["Binary Interactions","IntAct","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_binary_interactions.csv","filename":"arabidopsis_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_binary_interactions.stat.csv","filename":"arabidopsis_protein_binary_interactions.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"aa89157a618c64b929b1b094cab49c322b407ccd66cab306b6b3d91ad0c79168"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":404,"last_update":"2024-07-08T12:05:36.480679Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001055/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001055/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-08T13:28:04","modified":"2024-07-08T13:30:22.604Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Canonical (UniProtKB) Sequences dataset contains Arabidopsis thaliana [taxid:3702] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all chicken canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}],"keywords":["protein sequence","fasta","UniProtKB canonical accessions"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_canonicalsequences.fasta","filename":"arabidopsis_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_canonicalsequences.stat.csv","filename":"arabidopsis_protein_canonicalsequences.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"8e759889b34cbb35b48f85bec3e59eeb65282f2a04b57debf3ee05a54460d7fe"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":260,"last_update":"2024-07-08T13:30:22.604371Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001056/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001056/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-08T14:35:03","modified":"2024-07-08T14:39:43.781Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Arabidopsis Protein Citations dataset contains publication information for Arabidopsis thaliana [taxid:3702] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}],"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_uniprotkb.csv","filename":"arabidopsis_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_uniprotkb.stat.csv","filename":"arabidopsis_protein_citations_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"ff6bb10276e33a4d5a9984c837dc3b70dc91390b547dca55a448ec1a703a22c2"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":430,"last_update":"2024-07-08T14:39:43.781168Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001057/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001057/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Enzyme Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-08T14:41:55","modified":"2024-07-08T14:45:54.034Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Enzyme Annotation (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}],"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_enzyme_annotation_uniprotkb.csv","filename":"arabidopsis_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"arabidopsis_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"e878fb011e531aaba0f318d51b3c78ec0097e979bf47337c2b7792b655328715"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2024-07-08T14:45:54.034124Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001058/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001058/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Function (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-08T15:00:20","modified":"2024-07-08T15:02:28.559Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Function (UniProtKB) dataset contains biological function annotation for Arabidopsis thaliana [taxid:3702] protein accessions from the UniProtKB database.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein function","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_function_uniprotkb.csv","filename":"arabidopsis_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_function_uniprotkb.stat.csv","filename":"arabidopsis_protein_function_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"46f0bb00b3192624bdaff93791e3f3f3998a2ed86eb07cdc72e18acbb51d05cb"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":271,"last_update":"2024-07-08T15:02:28.559184Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001059/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001059/DRAFT","spec_version":"1.3.0","etag":"adf583da211b8a0b12e013a02316baf26a3c27f2cd15843f54842ad67907c1c8","provenance_domain":{"name":"Arabidopsis Gene Locus (Ensembl)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-08T15:17:44.182Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Gene Locus (Ensembl) contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_genelocus.csv","filename":"arabidopsis_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_genelocus.stat.csv","filename":"arabidopsis_protein_genelocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":325,"last_update":"2024-07-08T15:17:44.182397Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001060/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001060/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Gene Symbols (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-08T18:51:33","modified":"2024-07-08T19:05:39.084Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Arabidopsis Gene Symbols (NCBI RefSeq) dataset contains Arabidopsis thaliana [taxid:3702] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_genenames_refseq.csv","filename":"arabidopsis_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_genenames_refseq.stat.csv","filename":"arabidopsis_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"cca4ca18e1c9f1f43136a1ea399bb5a8bdf9a640303301b3a97ba6edf491fbd3"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":262,"last_update":"2024-07-08T19:05:39.084244Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001061/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001061/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-09T11:36:13.461Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Arabidopsis thaliana [taxid:3702] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_genenames_uniprotkb.csv","filename":"arabidopsis_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_genenames_uniprotkb.stat.csv","filename":"arabidopsis_protein_genenames_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"4ba78b18668c9e99eac441c6fa95337cb635afbce923c9f429a662a32435b71c"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":328,"last_update":"2024-07-09T11:36:13.461545Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001062/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001062/DRAFT","spec_version":"1.3.0","etag":"a56993448e80cb885c35c6d017b2f18948be2b49b097c25677f0f3b696822513","provenance_domain":{"name":"Arabidopsis N-Glycosylation Sequon","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-09T11:46:24","modified":"2024-07-09T11:52:11.846Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Arabidopsis thaliana [taxid:3702] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}],"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_glycosylation_motifs.csv","filename":"arabidopsis_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_glycosylation_motifs.stat.csv","filename":"arabidopsis_protein_glycosylation_motifs.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2024-07-09T11:52:11.846048Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001063/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001063/DRAFT","spec_version":"1.3.0","etag":"1c2e0c5fad793c93e89f2db38e0a245553aed4c7d050221657964e6f9af959e5","provenance_domain":{"name":"Human Protein Diseases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-09T15:16:45","modified":"2024-07-09T15:31:25.185Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Protein Diseases contains diseases associated with the Homo sapiens [taxid:9606] protein UniProtKB canonical accessions. The dataset also contains mapping of UniProtKB canonical accessions to the Disease Ontology (DO), Mondo and OMIM resources.\nIf you use this dataset please provide proper attribution to GlyGen and Alliance of Genome Resources."],"description_domain":{"keywords":["disease","human","mim","do","mondo"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_disease_alliance_genome.csv","filename":"human_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_disease_alliance_genome.stat.csv","filename":"human_protein_disease_alliance_genome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2024-07-09T15:31:25.185602Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001064/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001064/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Aradidopsis Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-10T11:06:37.073Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Gene Ontology (GO) dataset contains Arabidopsis thaliana [taxid:3702] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}],"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_go_annotation.csv","filename":"arabidopsis_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_go_annotation.stat.csv","filename":"arabidopsis_protein_go_annotation.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"36a9eeeb1cadd0c61b4e9a2e3144fdc75d69f8086f0289d6b60c2e7335766e16"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":277,"last_update":"2024-07-10T11:06:37.073265Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001065/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001065/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-10T11:26:31.727Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","contribution":["contributedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Information (NCBI RefSeq) dataset contains Arabidopsis thaliana [taxid:3702] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein information","protein length","NCBI RefSeq","protein summary"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_info_refseq.csv","filename":"arabidopsis_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_info_refseq.stat.csv","filename":"arabidopsis_protein_info_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"bfec8be568e49048afb225f7ccd373112d9dc1d1120e64e0b875aa927896d537"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-07-10T11:26:31.727888Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001066/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001066/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-10T11:44:14.728Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Information dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}],"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_info_uniprotkb.csv","filename":"arabidopsis_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_info_uniprotkb.stat.csv","filename":"arabidopsis_protein_info_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"485b72a5932f30e1f7645ce0e720f4806ac3daaeab62912805cbab08a3739d0e"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":294,"last_update":"2024-07-10T11:44:14.728116Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001067/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001067/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Proteome Masterlist (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-10T17:57:59.206Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Proteome Masterlist dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}],"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_masterlist.csv","filename":"arabidopsis_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_masterlist.stat.csv","filename":"arabidopsis_protein_masterlist.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"306487d461a5d08ab78733e11f1d143c027ec4e6e0f8c560ab8b6073797e055c"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":214,"last_update":"2024-07-10T17:57:59.206710Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001068/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001068/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis NCBI Protein Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis NCBI Protein Linkouts contains Arabidopsis thaliana [taxid:3702] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_proteinnames_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_proteinnames_refseq.csv"}},{"uri":{"filename":"chicken_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_ncbi_linkouts.csv","filename":"arabidopsis_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_ncbi_linkouts.stat.csv","filename":"arabidopsis_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T18:03:18.061455Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001070/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001070/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Reaction Participants (Rhea)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":[],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_participants_rhea.csv","filename":"arabidopsis_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_participants_rhea.stat.csv","filename":"arabidopsis_protein_participants_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T20:41:02.313081Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001071/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001071/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Protein Resource Ontology [Arabidopsis]","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-12T12:09:24.716Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Darren Natale","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"dan5@georgetown.edu"},{"name":"Matthew Campbell ","affiliation":"UniCarbKB","contribution":["contributedBy"],"email":"m.campbell2@griffith.edu.au"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for Arabidopsis thaliana [taxid:3702] proteins."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale) and a python script was used to convert the source file into a csv format."}],"keywords":["Proteoforms","PRO","UniCarbKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_pro_annotation.csv","filename":"arabidopsis_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_pro_annotation.stat.csv","filename":"arabidopsis_protein_pro_annotation.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"GlyGen_table_to_PRO.obo","uri":"https:/data.glygen.org/ln2downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"4f4f142b2c5b2c13a6a21830fac3e2ce809e555dc109d5c98a09f8c5cfb01933"},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":252,"last_update":"2025-03-12T12:09:24.716338Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001072/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001072/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Names (NCBI RefSeq)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Names (NCBI RefSeq) dataset contains Arabidopsis thaliana [taxid:3702] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_protein_xref_refseq.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_proteinnames_refseq.csv","filename":"arabidopsis_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_proteinnames_refseq.stat.csv","filename":"arabidopsis_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T20:41:02.887056Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001073/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001073/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein PTM Annotation (UniProtKB)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein PTM Annotation (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_ptm_annotation_uniprotkb.csv","filename":"arabidopsis_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_ptm_annotation_uniprotkb.stat.csv","filename":"arabidopsis_protein_ptm_annotation_uniprotkb.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T20:41:03.162154Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001074/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001074/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Reactions (Rhea)","version":"v-2.6.1","license":"","created":"","modified":"","contributors":[{"name":"","affiliation":"","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":[],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_reactions_rhea.csv","filename":"arabidopsis_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_reactions_rhea.stat.csv","filename":"arabidopsis_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T20:41:03.421635Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001075/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001075/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Recommended Names (UniProtKB)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Recommended Names (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702]  UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_recnames.csv","filename":"arabidopsis_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_recnames.stat.csv","filename":"arabidopsis_protein_recnames.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}]},"error_domain":{}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T20:43:12.065173Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001076/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001076/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Sequence Info (UniProtKB)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Sequence Info (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_sequenceinfo.csv","filename":"arabidopsis_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_sequenceinfo.stat.csv","filename":"arabidopsis_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T20:45:54.548637Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001077/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001077/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Signal Peptide","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Protein Signal Peptide dataset contains Arabidopsis thaliana [taxid:3702] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}},{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}},{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}},{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_annotation.csv","filename":"arabidopsis_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_peptidesequences.fasta","filename":"arabidopsis_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_cleavedsequences.fasta","filename":"arabidopsis_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_fullsequences.fasta","filename":"arabidopsis_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_annotation.stat.csv","filename":"arabidopsis_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_peptidesequences.stat.csv","filename":"arabidopsis_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_cleavedsequences.stat.csv","filename":"arabidopsis_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_signalp_fullsequences.stat.csv","filename":"arabidopsis_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T20:45:54.864432Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001078/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001078/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Arabidopsis Protein Site Annotation","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-25T19:43:01.993Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Site Annotation (UniProtKB) dataset contains arabidopsis [taxid:3702] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range.  If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","input_list":[]}],"keywords":["site annotation","amino acid range","UniProtKB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_site_annotation_uniprotkb.csv","filename":"arabidopsis_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_site_annotation_uniprotkb.stat.csv","filename":"arabidopsis_protein_site_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"2ae89a3502d20d7d8f12b31c519ae7a2e1b008d405fb3347511007b20e57e95a"},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":316,"last_update":"2024-07-25T19:43:01.993535Z","access_count":9},{"object_id":"https://biocomputeobject.org/GLY_001079/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001079/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Protein Submitted Names (UniProtKB)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Arabidopsis thaliana [taxid:3702] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_submittednames.csv","filename":"arabidopsis_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_submittednames.stat.csv","filename":"arabidopsis_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T21:38:43.935064Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001080/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001080/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Transcript Locus (Ensembl Transcript coordinates)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-11-04T12:27:54.952Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Transcript Locus (Ensembl Transcript coordinates) dataset contains UniProtKB Arabidopsis thaliana [taxid:3702] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Ensembl and GlyGen. "],"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are mapped to ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file, and then maps any UniProtKB isoforms to the UniProtKB canonical accession. The transcript ID is then used to extract the transcript's chromosome, start position, end position and forward/reverse strand data from the Ensembl gene annotation GFF3 file which has been converted to a TSV file. The extracted data is then used to create the csv dataset. "}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_transcriptlocus.csv","filename":"arabidopsis_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_transcriptlocus.stat.csv","filename":"arabidopsis_protein_transcriptlocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"867732829eb2b2a0d5751511c3aec461b35dbcb1528bcb9167fb7dbb81edb78b"},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":505,"last_update":"2025-11-04T12:27:54.952834Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001081/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001081/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref BRENDA","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniprotKB Xref BRENDA contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_brenda.csv","filename":"arabidopsis_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_brenda.stat.csv","filename":"arabidopsis_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T21:38:44.430850Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001082/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001082/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref CAZy","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniprotKB Xref CAZy contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_cazy.csv","filename":"arabidopsis_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_cazy.stat.csv","filename":"arabidopsis_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T21:38:44.698683Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001083/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001083/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref CDD","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref CDD contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_cdd.csv","filename":"arabidopsis_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_cdd.stat.csv","filename":"arabidopsis_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T21:38:44.958052Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001084/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001084/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref ChEMBL","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniprotKB Xref ChEMBL contains Homo sapiens [taxid:3702] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_chembl.csv","filename":"arabidopsis_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_chembl.stat.csv","filename":"arabidopsis_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"cyruschauyeung","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-10T21:38:45.210997Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001085/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001085/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref NCBI Gene","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T17:52:16.286Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref NCBI Gene dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["gene id","NCBI gene","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_geneid.csv","filename":"arabidopsis_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_protein_xref_geneid.stat.csv","filename":"arabidopsis_protein_xref_geneid.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"b6a7ec881e02187d7a6ddc421d41b6a98d332fe6e5ac7dbd9e8183be9e90b2e9"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":518,"last_update":"2024-07-11T17:52:16.286285Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001086/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001086/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref IntAct","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T18:00:58.848Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref IntAct dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_intact.csv","filename":"arabidopsis_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_intact.stat.csv","filename":"arabidopsis_protein_xref_intact.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"7dbebe725f4cdab33b38b9a0f8234d64264e2143335ffb4968721f8a73c7d403"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":543,"last_update":"2024-07-11T18:00:58.848642Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001087/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001087/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-03-15T12:05:44.324142","modified":"2024-07-11T18:21:02.884Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref InterPro contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}],"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_interpro.csv","filename":"arabidopsis_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_interpro.stat.csv","filename":"arabidopsis_protein_xref_interpro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"360c3f7cb6005dd80013217e92c633d9f97c61bc12af4362a83beb80ff11c2c9"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":477,"last_update":"2024-07-11T18:21:02.884075Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001088/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001088/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref KEGG PATHWAY","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T18:29:55.482Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref KEGG PATHWAY contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["pathways","reactions","KEGG Pathway","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_kegg.csv","filename":"arabidopsis_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_kegg.stat.csv","filename":"arabidopsis_protein_xref_kegg.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"6d20b867369d9e140dbf2b03c1b91983b25abcd52e1b1d563128ed4708d57d0e"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":422,"last_update":"2024-07-11T18:29:55.482198Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001089/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001089/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref OMA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T18:39:33.566Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref OMA contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["orthologs","OMA","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_oma.csv","filename":"arabidopsis_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_oma.stat.csv","filename":"arabidopsis_protein_xref_oma.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"50a80e75d06dec9aceb545646d721d89aad3021b29ebb11126d270043e3deea3"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":372,"last_update":"2024-07-11T18:39:33.566294Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001090/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001090/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref OrthoDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T19:08:27.583Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref OrthoDB contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["orthologs","OrthoDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_orthodb.csv","filename":"arabidopsis_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_orthodb.stat.csv","filename":"arabidopsis_protein_xref_orthodb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"73d3febd2837e22fcd5caaf1457f2e27ce8e0810f56ba873b910f83b3babd858"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":438,"last_update":"2024-07-11T19:08:27.583886Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001091/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001091/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref PANTHER","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:05:21.740Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref PANTHER contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein family","PANTHER","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_panther.csv","filename":"arabidopsis_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_panther.stat.csv","filename":"arabidopsis_protein_xref_panther.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"3aa92c3d49b8723f3b0284da5534bcbdf54be48adceeeaa73077503a06fc9883"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":477,"last_update":"2024-07-11T20:05:21.740765Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001092/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001092/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Glycosyltransferases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:11:51.972Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Hayley Dingerdissen","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"hmhamilt@gwmail.gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycosyltransferases dataset contains list of Arabidopsis thaliana [taxid:3702] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the Arabidopsis proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\" Arabidopsis thaliana [taxid:3702] \". To retrieve the list of all human glycosyltransferases, the full list of human proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_glycosyltransferase.csv","filename":"arabidopsis_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_glycosyltransferase.stat.csv","filename":"arabidopsis_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"e124b3446c5dfacaa86cade8bff83e729c7ec661b5020293c59e7e8578aa6764"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":2020,"last_update":"2024-07-11T20:11:51.972069Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001093/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001093/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:19:31.466Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref PDB contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein 3D structure","RCSB PDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_pdb.csv","filename":"arabidopsis_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_pdb.stat.csv","filename":"arabidopsis_protein_xref_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"4e05137a2b1abab951465123b116bc971de2f2fcd6b9998dcc61caa9b2b671fa"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":403,"last_update":"2024-07-11T20:19:31.466345Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001094/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001094/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref Pfam","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:26:10.639Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref Pfam contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein family","Pfam","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_pfam.csv","filename":"arabidopsis_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_pfam.stat.csv","filename":"arabidopsis_protein_xref_pfam.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"1f54bf9e50c2a75aa2f6c8b85e884ec1920fb15affd212c8fe6d252f4f4d6ad9"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":402,"last_update":"2024-07-11T20:26:10.639371Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001095/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001095/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref PRO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:31:00.422Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniprotKB Xref PRO contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein ontology","PRO","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_pro.csv","filename":"arabidopsis_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_pro.stat.csv","filename":"arabidopsis_protein_xref_pro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"e037c8f59d6254ad5aead4d748916b2c24640a60ec52cfd3552953a5419da922"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":401,"last_update":"2024-07-11T20:31:00.422696Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001096/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001096/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:37:46.613Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniprotKB Xref RefSeq contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein accessions","RefSeq","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_refseq.csv","filename":"arabidopsis_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_refseq.stat.csv","filename":"arabidopsis_protein_xref_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"50d8e536ba1490d539462b561f1e98092db72230160f1f6e9c8d7a7afbbdabcf"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":650,"last_update":"2024-07-11T20:37:46.613542Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001097/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001097/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:41:41.199Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","contribution":["contributedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref Rhea contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["reactions","Rhea","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_rhea.csv","filename":"arabidopsis_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_rhea.stat.csv","filename":"arabidopsis_protein_xref_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"4b117e8c90ab306d8dbb075a192696399d8d34e0a23daf550739370857f8fa74"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":260,"last_update":"2024-07-11T20:41:41.199699Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001098/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001098/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:45:57.019Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_uniprotkb.csv","filename":"arabidopsis_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_xref_uniprotkb.stat.csv","filename":"arabidopsis_protein_xref_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"542fe7ffe84e923bc3677c730981c1b550f38628c6c8f08f1f813a7fa841203c"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":268,"last_update":"2024-07-11T20:45:57.019353Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001099/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001099/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Glycohydrolases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-11T20:51:21.521Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycohydrolases dataset contains a list of Arabidopsis thaliana [taxid:3702] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_glycohydrolase.csv","filename":"arabidopsis_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.6.1/reviewed/arabidopsis_protein_glycohydrolase.stat.csv","filename":"arabidopsis_protein_glycohydrolase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"235f9ac42c07056fc334658801bec97d9b6d2c7cebb1062d15951b32bf9545e2"},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-07-11T20:51:21.521504Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001100/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001100/DRAFT","spec_version":"1.3.0","etag":"ad55c0d59eb79d446cb9c4e15040f25f8979d4072f7d519f44097cadebc7bbd4","provenance_domain":{"name":"Arabidopsis Glycosylation Sites (GlyConnect) ","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-02-10T10:16:50.152756","modified":"2024-07-23T14:22:11.963Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycosylation Sites (GlyConnect) dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy: Arabidopsis thaliana). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (arabidopsis_proteoform_glycosylation_sites_glyconnect.1.log)"}],"keywords":["glycosylation","reported glycosylation"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_04_02/cellosaurus.txt"}},{"uri":{"filename":"glyconnect_arabidopsis.json","uri":"https:/data.glygen.org/ln2downloads/glyconnect/2024_04_02/glyconnect_arabidopsis.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_glyconnect.csv","filename":"arabidopsis_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":544,"last_update":"2024-07-23T14:22:11.963578Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001101/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001101/DRAFT","spec_version":"1.3.0","etag":"33e5992d598fab9bdd17c57e3bf6018226fa19e8bc7eaf47e4b64e8f025bf18e","provenance_domain":{"name":"Arabidopsis Proteoform Citations (GlyConnect)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-28T10:49:06.505148","modified":"2024-07-23T14:32:33.676Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}],"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_proteoform_glycosylation_sites_glyconnect.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":446,"last_update":"2024-07-23T14:32:33.676760Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001102/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001102/DRAFT","spec_version":"1.3.0","etag":"309d52e2057213c122fb1821fb663301e8941cf70ba2ab12c56b4a245d924c48","provenance_domain":{"name":"Arabidopsis Glycosylation Sites (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.909814","modified":"2026-08-19T10:01:14.195Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jasmine Young","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"jasmine@rcsb.rutgers.edu"},{"name":"Chenghua Shao","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"chenghua@rcsb.rutgers.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycosylation Sites (RCSB PDB) dataset contains arabidopsis [taxid:3702] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"input_list":[]}],"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_04_02/cellosaurus.txt"}},{"uri":{"filename":"N-linked-ARG-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ARG-details"}},{"uri":{"filename":"N-linked-ASN-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ASN-details"}},{"uri":{"filename":"O-linked-ASP-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-ASP-details"}},{"uri":{"filename":"O-linked-GLU-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-GLU-details"}},{"uri":{"filename":"O-linked-SER-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-SER-details"}},{"uri":{"filename":"O-linked-THR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-THR-details"}},{"uri":{"filename":"O-linked-TYR-details","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-TYR-details"}},{"uri":{"filename":"pdb_chain_uniprot.csv","uri":"https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_pdb.csv","filename":"arabidopsis_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_pdb.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":513,"last_update":"2026-08-19T10:01:14.195069Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001103/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001103/DRAFT","etag":"e1d415b01b9601c8d474b0444ffdd910","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Proteoform Glycosylation Citations (UniProtKB)","version":"v-x.x.x","created":"2021-06-03T16:32:02.053252","modified":"2024-05-17T11:24:04.661Z","contributors":[{"name":"Jeet Vora","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Proteoform Glycosylation Citations (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] citation details of the publications present in the dataset Arabidopsis Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000038)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"arabidopsis_proteoform_glycosylation_sites_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_uniprotkb.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-23T14:36:04.555411Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001104/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001104/DRAFT","etag":"fa7cc765dccf27c856839381e88e4a48","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-27T21:08:01.227Z","modified":"2024-05-17T11:24:10.298Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","orcid":"","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Arabidopsis O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000708, contributed by Jungfeng Ma's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-23T14:39:17.825433Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001105/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001105/DRAFT","spec_version":"1.3.0","etag":"36691bd81d12be6d9af07ae74aa9b68b7413cc2f472fcea892505926c70c935c","provenance_domain":{"name":"Arabidopsis O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-12-05T18:55:37.672Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Arabidopsis thaliana (taxid:3702) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":[null,"O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_protein_info_uniprotkb.csv"}},{"uri":{"filename":"arabidopsis_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_protein_masterlist.csv"}},{"uri":{"filename":"arabidopsis_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/sample_mapping.csv"}},{"uri":{"filename":"ambiguous_sites.csv","uri":"https:/data.glygen.org/ln2downloads/atlas_oglcnac/2024_04_08/ambiguous_sites.csv"}},{"uri":{"filename":"unambiguous_sites.csv","uri":"https:/data.glygen.org/ln2downloads/atlas_oglcnac/2024_04_08/unambiguous_sites.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_04_02/cellosaurus.txt"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2024-12-05T18:55:37.672924Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001106/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001106/DRAFT","etag":"e39487040bdb9b213f11d9eeeeb33be8","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis O-GlcNAc Glycosylation Citations (MCW)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-07-15T16:28:21.779974","modified":"2024-05-17T11:24:03.245Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Arabidopsis O-GlcNAc Glycosylation Sites (MCW)  https://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"arabidopsis_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-23T14:46:35.523304Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001107/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001107/DRAFT","spec_version":"1.3.0","etag":"3b2df449680ea243b7270674a685f22247bdb9ada7c45218a157068507f4a344","provenance_domain":{"name":"Arabidopsis O-GlcNAc Glycosylation Sites (MCW)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-07-09T13:50:43.000375","modified":"2024-12-05T18:50:04.759Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis O-GlcNAc Glycosylation Sites (MCW) contains Arabidopsis thaliana (taxid:3702) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The current dataset has 4997 proteins with O-GlcNAc modifications. Out of which 3262 proteins have no site information where as 1735 proteins have 6722 sites.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Arabidopsis O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s arabidopsis protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to arabidopsis species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding arabidopsis UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a total of 2,237 proteins had an O-GlcNAc score of 3 or under, meaning that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation.","The log file - https://data.glygen.org/ln2data/releases/data/v-1.12.3/logs/arabidopsis.log contains the entries that were excluded from the output file along with the reason for exclusion.","The orginal unprocessed dataset in excel format can be found at https://figshare.com/articles/The_arabidopsis_O-GlcNAcome_database/12443495/4"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field."}],"keywords":["O-GlcNAc"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_protein_info_uniprotkb.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_protein_info_uniprotkb.csv"}},{"uri":{"filename":"arabidopsis_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_protein_masterlist.csv"}},{"uri":{"filename":"arabidopsis_protein_recnames.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_protein_recnames.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_04_02/cellosaurus.txt"}},{"uri":{"filename":"arabidopsis_o_glcnacome_mcw.csv","uri":"https:/data.glygen.org/ln2downloads/mcw_oglcnac/2024_04_02/arabidopsis_o_glcnacome_mcw.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":3633,"last_update":"2024-12-05T18:50:04.759831Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001108/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001108/DRAFT","spec_version":"1.3.0","etag":"9deeb21363f6e457a098bb7ce924ac6287ce659c7be1bcd2c40e2da66b6072fb","provenance_domain":{"name":"Arabidopsis Proteoform Phosphorylation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T08:00:04.645468","modified":"2025-10-09T14:46:53.700Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Proteoform Phosphorylation Citations (UniProtKB) dataset contains arabidopsis [taxid:3702] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"arabidopsis_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"arabidopsis_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":350,"last_update":"2025-10-09T14:46:53.700751Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001109/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001109/DRAFT","etag":"ff080977485178e14e67eeee53a21448","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Phosphorylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:39.000407","modified":"2024-05-17T11:23:54.582Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Phosphorylation Sites (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"arabidopsis_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"arabidopsis_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-23T14:59:15.739399Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001110/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001110/DRAFT","etag":"9c7c20ca737fa1ec026d08605ed9d947","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.905721","modified":"2024-05-17T11:23:50.059Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycosylation Sites (UniProtKB) dataset contains arabidopsis [taxid:3702] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Arabidopsis thaliana proteome release."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"glycosylation_subtype.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/glycosylation_subtype.csv"}},{"uri":{"filename":"n_sequon_info.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/n_sequon_info.csv"}},{"uri":{"filename":"sample_mapping.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/sample_mapping.csv"}},{"uri":{"filename":"cellosaurus.txt","uri":"https:/data.glygen.org/ln2downloads/cellosaurus/2024_04_02/cellosaurus.txt"}},{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-arabidopsis-thaliana.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_uniprotkb.csv","filename":"arabidopsis_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-23T15:04:16.738669Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001111/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001111/DRAFT","spec_version":"1.3.0","etag":"197fcea719ad120fb353daf55db935464340328b51a9e63023d9a6ea8e6b3ad3","provenance_domain":{"name":"Arabidopsis Proteoform Phosphorylation Citations (iPTMnet)","version":"v-x.x.x","created":"2021-06-03T17:29:17.656153","modified":"2024-12-05T19:41:11.034Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Proteoform Citations (iPTMNet) contains Arabidopsis thaliana [taxid:3702] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_proteoform_phosphorylation_sites_iptmnet.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_phosphorylation_sites_iptmnet.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"arabidopsis_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"arabidopsis_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":434,"last_update":"2024-12-05T19:41:11.034843Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001112/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001112/DRAFT","etag":"f1d6e77a35500a9e5617f1fe6acae714","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Phosphorylation Sites (iPTMNet)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-08-17T16:43:14.212000","modified":"2024-05-21T14:45:28.794Z","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Phosphorylation Sites (iPTMNet) dataset contains Arabidopsis thaliana [taxid:3702] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_phosphorylation_sites_iptmnet.csv","filename":"arabidopsis_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"arabidopsis_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"arabidopsis_protein_masterlist.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/arabidopsis_protein_masterlist.csv"}},{"uri":{"filename":"ptm.txt","uri":"https:/data.glygen.org/ln2downloads/iptmnet/2024_04_02/ptm.txt"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-23T15:10:13.109948Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001113/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001113/DRAFT","spec_version":"1.3.0","etag":"64d77a35c57e5fd0a1ea7e4d898da1db4b9929febd5addad36e778aa98c3ae4e","provenance_domain":{"name":"Human Glycosylation Sites (CarbBank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-10T21:01:25","modified":"2024-12-10T21:43:00.169Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human CarbBank Glycosylation Sites dataset contains information on Homo sapiens [taxid:9606] glycan and glycosylation sites mapped to the UniProtKB canonical accessions derived from the CarbBank resource. CarbBank was a pioneering database that cataloged carbohydrate structures and related biochemical information. Although no longer actively maintained, CarbBank laid the groundwork for modern glycoinformatics tools and databases, influencing subsequent efforts to document carbohydrate-related data systematically. Please cite GlyGen and CarbBank if you use this dataset."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script performs QC steps and creates a proteoform dataset according to the GlyGen data model."}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_carbbank.csv","filename":"human_proteoform_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_carbbank.stat.csv","filename":"human_proteoform_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":699,"last_update":"2024-12-10T21:43:00.169675Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_001114/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001114/DRAFT","spec_version":"1.3.0","etag":"dce43c05aad4dc58792887c7e4a57a0cd18b8d179d766c087e31a218a7183735","provenance_domain":{"name":"Mouse Glycosylation Sites (CarbBank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-10T21:01:50","modified":"2024-12-10T21:44:26.970Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse CarbBank Glycosylation Sites dataset contains information on Mus musculus [taxid:10090] glycan and glycosylation sites mapped to the UniProtKB canonical accessions derived from the CarbBank resource. CarbBank was a pioneering database that cataloged carbohydrate structures and related biochemical information. Although no longer actively maintained, CarbBank laid the groundwork for modern glycoinformatics tools and databases, influencing subsequent efforts to document carbohydrate-related data systematically. Please cite GlyGen and CarbBank if you use this dataset."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script performs QC steps and creates a proteoform dataset according to the GlyGen data model."}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_carbbank.csv","filename":"mouse_proteoform_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_carbbank.stat.csv","filename":"mouse_proteoform_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":701,"last_update":"2024-12-10T21:44:26.970531Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001115/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001115/DRAFT","spec_version":"1.3.0","etag":"9c502b31204bb571e998baffe20bd9c0e73300a959f62b32d75d4eeae05e7f81","provenance_domain":{"name":"Rat O-GlcNAc Glycosylation Sites (Carbbank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-25T20:59:00","modified":"2024-10-25T20:59:16.943Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script performs QC steps and creates a proteoform dataset according to the GlyGen data model."}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_carbbank.csv","filename":"rat_proteoform_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_carbbank.stat.csv","filename":"rat_proteoform_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T20:59:16.943360Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001116/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001116/DRAFT","spec_version":"1.3.0","etag":"629aa58c91469a78cfe75f20a1aa8314b593a86c17777e96d70a43700bcc222b","provenance_domain":{"name":"Yeast Glycosylation Sites (CarbBank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-10T21:02:33","modified":"2024-12-10T21:45:47.463Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast CarbBank Glycosylation Sites dataset contains information on Saccharomyces cerevisiae S288C [taxid:559292] glycan and glycosylation sites mapped to the UniProtKB canonical accessions derived from the CarbBank resource. CarbBank was a pioneering database that cataloged carbohydrate structures and related biochemical information. Although no longer actively maintained, CarbBank laid the groundwork for modern glycoinformatics tools and databases, influencing subsequent efforts to document carbohydrate-related data systematically. Please cite GlyGen and CarbBank if you use this dataset."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script performs QC steps and creates a proteoform dataset according to the GlyGen data model."}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_carbbank.csv","filename":"yeast_proteoform_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_carbbank.stat.csv","filename":"yeast_proteoform_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":723,"last_update":"2024-12-10T21:45:47.463351Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001117/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001117/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Human UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-24T10:45:20.865Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniProtKB Xref AlphaFold contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_alphafolddb.csv","filename":"human_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_alphafolddb.stat.csv","filename":"human_protein_xref_alphafolddb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{},"etag":"80bc48f45e8651d02f2963ccceec6c4ae5f1e40d40619c37b01672cc545b4aa8"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":373,"last_update":"2024-07-24T10:45:20.865903Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001118/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001118/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Mouse UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-24T13:29:30.822Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse UniProtKB Xref AlphaFold contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_alphafolddb.csv","filename":"mouse_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_alphafolddb.stat.csv","filename":"mouse_protein_xref_alphafolddb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"6f1169afc6e0b4be9c838796023988fad6272c6c295f63b80682cb4179f02eee"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":374,"last_update":"2024-07-24T13:29:30.822511Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001119/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001119/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Rat UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat UniProtKB Xref AlphaFold contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"","uri":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_alphafolddb.csv","filename":"rat_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_alphafolddb.stat.csv","filename":"rat_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-24T10:59:58.860995Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001120/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001120/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly UniProtKB Xref AlphaFold contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"","uri":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_alphafolddb.csv","filename":"fruitfly_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_alphafolddb.stat.csv","filename":"fruitfly_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-24T11:05:42.202350Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001121/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001121/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Yeast UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref AlphaFold contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"","uri":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_alphafolddb.csv","filename":"yeast_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_alphafolddb.stat.csv","filename":"yeast_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-24T12:37:06.523093Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001122/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001122/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Dicty UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-26T12:35:21.904Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty UniProtKB Xref AlphaFold contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_xref_alphafolddb.csv","filename":"dicty_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_xref_alphafolddb.stat.csv","filename":"dicty_protein_xref_alphafolddb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{},"etag":"303c4082a17f4dcb507165c6dd9a9c8b62d9d472880b3cb26f02ccf79b9612ad"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":385,"last_update":"2024-07-26T12:35:21.904468Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001123/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001123/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref AlphaFold contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"","uri":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_alphafolddb.csv","filename":"pig_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_alphafolddb.stat.csv","filename":"pig_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-24T13:04:50.570906Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001124/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001124/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref AlphaFold contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"","uri":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_alphafolddb.csv","filename":"chicken_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_alphafolddb.stat.csv","filename":"chicken_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-24T13:10:10.617736Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001125/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001125/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref AlphaFold contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"","uri":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_alphafolddb.csv","filename":"arabidopsis_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_alphafolddb.stat.csv","filename":"arabidopsis_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-24T13:21:11.370272Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001126/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001126/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"GlyGen-Flybase Crossreferences Mapping","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-24T13:28:13.683Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The GlyGen-Flybase Cross-references Mapping dataset contains GlyGen's Drosophila melanogaster [taxid:7227] UniProtKB accessions cross-referenced to FlyBase database identifiers. The dataset is created for the Flybase database to crosslink their protein page links to GlyGen protein pages, and is formatted as per the 'Links from FlyBase' guidelines where the DbName is GlyGen. The *linkout.tsv is four column TSV, Column 1 - FlyBase ID, Column 2 - DBNAME, Column 3 - DBID, Column 4 - DBURL. The database information file is named glygen_dbinfo.tsv that contains five lines and can be accessed from GlyGen Sharepoint."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the fruitfly UniProtKB GlyGen accessions, maps them to their Flybase IDs, and extracts the data into the tsv dataset file."}],"keywords":["crossreferences","fruitfly","GlyGen","Flybase"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_glygen_flybase_linkout.tsv","filename":"protein_glygen_flybase_linkout.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_glygen_flybase_linkout.stat.csv","filename":"protein_glygen_flybase_linkout.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-Flybase Crossreferences","category_name":"tag"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"external","category_name":"scope"}]}}],"error_domain":{},"etag":"6d729054a63db7bf8e2b6041a37b9a1e82bca8b9780b6b546264598951fbbd48"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":616,"last_update":"2024-07-24T13:28:13.683584Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001127/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001127/DRAFT","spec_version":"1.3.0","etag":"679aa0353887cd1d6c49301664998614f4f38d03a0f2873357afd31cd3b0b73d","provenance_domain":{"name":"Human UniProtKB Xref MassIVE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-25T16:13:28","modified":"2024-07-25T16:15:21.219Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniProtKB Xref MassIVE dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to MassIVE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Mass Spectrometry Interactive Virtual Environment (MassIVE) database is a community resource developed to promote the global, free exchange of mass spectrometry data."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to MassIVE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["proteomics","mass spectrometry","massive","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_massive.csv","filename":"human_protein_xref_massive.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_massive.stat.csv","filename":"human_protein_xref_massive.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MassIVE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":429,"last_update":"2024-07-25T16:15:21.219703Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001128/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001128/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Human UniProtKB Xref PRIDE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-25T14:16:09.397Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniProtKB Xref PRIDE contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to PRIDE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The PRoteomics IDEntifications (PRIDE) Archive database is a public data repository for mass spectrometry proteomics data, including protein and peptide identifications, expression values, post-translational modifications and supporting mass spectra evidence."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRIDE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["proteomics","mass spectrometry","pride","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_pride.csv","filename":"human_protein_xref_pride.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_pride.stat.csv","filename":"human_protein_xref_pride.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRIDE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"97eae17fca600b66ab7bf4e2815caee861e40cba69eb19c6563e43a4d125c11d"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2024-07-25T14:16:09.397225Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001129/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001129/DRAFT","spec_version":"1.3.0","etag":"7fc314ed6eecd22391d083057cb4ae8f661d66300c65dce92ef1401ba873cb43","provenance_domain":{"name":"Mouse UniProtKB Xref PRIDE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-27T12:01:36","modified":"2024-08-27T12:06:50.348Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse UniProtKB Xref PRIDE contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to PRIDE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The PRoteomics IDEntifications (PRIDE) Archive database is a public data repository for mass spectrometry proteomics data, including protein and peptide identifications, expression values, post-translational modifications and supporting mass spectra evidence."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRIDE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["proteomics","mass spectrometry","cross-reference","pride"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_pride.csv","filename":"mouse_protein_xref_pride.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_pride.stat.csv","filename":"mouse_protein_xref_pride.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRIDE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2024-08-27T12:06:50.348085Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001130/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001130/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref PRIDE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-25T15:41:26.337Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref PRIDE contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to PRIDE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The PRoteomics IDEntifications (PRIDE) Archive database is a public data repository for mass spectrometry proteomics data, including protein and peptide identifications, expression values, post-translational modifications and supporting mass spectra evidence."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRIDE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["proteomics","mass spectrometry","pride","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_pride.csv","filename":"arabidopsis_protein_xref_pride.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_pride.stat.csv","filename":"arabidopsis_protein_xref_pride.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRIDE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"0dfb0abb469674b32e31ef07b4bb39c524ef99a33bd70dbe69b8d6d8f82031cd"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":520,"last_update":"2024-07-25T15:41:26.337424Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001131/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001131/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Yeast UniProtKB Xref PRIDE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-25T15:55:15.515Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref PRIDE contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to PRIDE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The PRoteomics IDEntifications (PRIDE) Archive database is a public data repository for mass spectrometry proteomics data, including protein and peptide identifications, expression values, post-translational modifications and supporting mass spectra evidence."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRIDE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["proteomics","mass spectrometry","pride","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_pride.csv","filename":"yeast_protein_xref_pride.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_pride.stat.csv","filename":"yeast_protein_xref_pride.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRIDE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"543bc4bc3cb1e5bea7d85c952c363d5fd3fb3c554957c3e8fd26f2bda48b8cfe"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":526,"last_update":"2024-07-25T15:55:15.515261Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001132/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001132/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Pig UniProtKB Xref PRIDE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref PRIDE contains Sus scrofa [taxid:9606] UniProtKB canonical accessions cross-referenced to PRIDE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The PRoteomics IDEntifications (PRIDE) Archive database is a public data repository for mass spectrometry proteomics data, including protein and peptide identifications, expression values, post-translational modifications and supporting mass spectra evidence."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRIDE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["proteomics","mass spectrometry","pride","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRIDE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_pride.csv","filename":"pig_protein_xref_pride.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_pride.stat.csv","filename":"pig_protein_xref_pride.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-07-25T15:06:45.427961Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001133/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001133/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Rat UniProtKB Xref PRIDE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-25T16:11:15.238Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat UniProtKB Xref PRIDE contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to PRIDE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The PRoteomics IDEntifications (PRIDE) Archive database is a public data repository for mass spectrometry proteomics data, including protein and peptide identifications, expression values, post-translational modifications and supporting mass spectra evidence."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRIDE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["proteomics","mass spectrometry","pride","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_pride.csv","filename":"rat_protein_xref_pride.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_pride.stat.csv","filename":"rat_protein_xref_pride.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":" Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRIDE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"f51458f2ea90e7e29e6b5e9aae4d09ddb96d2e754c19381f97a495c742addcb0"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":510,"last_update":"2024-07-25T16:11:15.238408Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001134/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001134/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly UniProtKB Xref PRIDE","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-25T16:13:11.606Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly UniProtKB Xref PRIDE contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions cross-referenced to PRIDE database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The PRoteomics IDEntifications (PRIDE) Archive database is a public data repository for mass spectrometry proteomics data, including protein and peptide identifications, expression values, post-translational modifications and supporting mass spectra evidence."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRIDE database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["proteomics","mass spectrometry","pride","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pride.csv","filename":"fruitfly_protein_xref_pride.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pride.stat.csv","filename":"fruitfly_protein_xref_pride.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRIDE cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"58039cb28540cf137ed321381f0f0e2e36e3398b7d2aa18fc9cddf1eacdd8d54"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":520,"last_update":"2024-07-25T16:13:11.606359Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001135/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001135/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Proteoform Citations (GlyConnect)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-26T11:50:49.140Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}],"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"chicken_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"chicken_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"811d92150a96683dc1f7854cdc3c272018f229b0ed8191eae51c74acf0d94810"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":442,"last_update":"2024-07-26T11:50:49.140466Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001136/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001136/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Xref O-GlcNAcAtlas","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-07-26T12:01:27.124Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Arabidopsis Xref O-GlcNAcAtlas dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions mapped to the O-GlcNAcAtlas accessions."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the O-GlcNAcAtlas Database accessions"}],"keywords":["Xref","O-GlcNAc","O-GlcNAc Atlas"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_oglcnac_atlas.csv","filename":"arabidopsis_protein_xref_oglcnac_atlas.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_oglcnac_atlas.stat.csv","filename":"arabidopsis_protein_xref_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"ac84851cea3774459354b5bff4c7d4c6f6d0302197d6e834a6f73b000ef02b43"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":152,"last_update":"2024-07-26T12:01:27.124216Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001137/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001137/DRAFT","spec_version":"1.3.0","etag":"a2434fb69960b605061655e9ee97fcdb348d828fc6851566f5fb74a16ab3a053","provenance_domain":{"name":"Arabidopsis UniProtKB xref GlyConnect","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-07-26T12:19:19","modified":"2026-03-23T20:05:32.076Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB xref GlyConnect dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_glyconnect.csv","filename":"arabidopsis_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_glyconnect.stat.csv","filename":"arabidopsis_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":188,"last_update":"2026-03-23T20:05:32.076768Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001138/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001138/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref O-GlcNAc (MCW)","version":"v-x.x.x","license":"httpss://creativecommons.org/licenses/by/4.0/","modified":"2024-07-29T20:25:06.532Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref O-GlcNAc (MCW) contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O-GlcNAc(MCW) is a database for O-GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["Arabidopsis","O-GlcNAc (MCW)","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_oglcnac_mcw.csv","filename":"arabidopsis_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_oglcnac_mcw.stat.csv","filename":"arabidopsis_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"269fa0bc3824458b4786593817f90866873985ad56382671b96f4f370c9f2f61"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":373,"last_update":"2024-07-29T20:25:06.532535Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001139/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001139/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Chicken UniProtKB Xref O-GlcNAc (MCW)","version":"v-x.x.x","license":"httpss://creativecommons.org/licenses/by/4.0/","modified":"2024-07-29T20:26:44.436Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref O-GlcNAc (MCW) contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O-GlcNAc(MCW) is a database for O-GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["Chicken","O-GlcNAc (MCW)","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_oglcnac_mcw.csv","filename":"chicken_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_oglcnac_mcw.stat.csv","filename":"chicken_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"13a615130a818e2cd99977e1834c70b159844e45fad923f2263a026693f7819e"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":362,"last_update":"2024-07-29T20:26:44.436277Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001140/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001140/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-07-31T17:06:55.479Z"},"usability_domain":["The Arabidopsis GlyGen-PDB Cross References dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_pdb_map.csv","filename":"arabidopsis_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_pdb_map.stat.csv","filename":"arabidopsis_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":279,"last_update":"2024-07-31T17:06:55.479211Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001141/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001141/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Mouse GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The mouse GlyGen-PDB Cross References dataset contains Mus musculus [taxid:10090] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_pdb_map.csv","filename":"mouse_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_pdb_map.stat.csv","filename":"mouse_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T00:24:42.767940Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001142/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001142/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Yeast GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The yeast GlyGen-PDB Cross References dataset contains Saccharomyces cerevisiaels [taxid:559292] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_pdb_map.csv","filename":"yeast_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_pdb_map.stat.csv","filename":"yeast_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T00:32:08.685204Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001143/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001143/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Rat GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The rat GlyGen-PDB Cross References dataset contains Rattus norvegicus [taxid:10116] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_pdb_map.csv","filename":"rat_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_pdb_map.stat.csv","filename":"rat_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T00:36:36.576919Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001144/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001144/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Fruitfly GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The fruitfly GlyGen-PDB Cross References dataset contains Drosophila melanogaster [taxid:7227] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_pdb_map.csv","filename":"fruitfly_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_pdb_map.stat.csv","filename":"fruitfly_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T00:40:26.778681Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001145/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001145/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Human GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The human GlyGen-PDB Cross References dataset contains Homo sapiens [taxid:9606] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_pdb_map.csv","filename":"human_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_pdb_map.stat.csv","filename":"human_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T00:44:58.542351Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001146/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001146/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Pig GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The pig GlyGen-PDB Cross References dataset contains Sus scrofa [taxid:9823] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_pdb_map.csv","filename":"pig_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_pdb_map.stat.csv","filename":"pig_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T00:48:53.684517Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001147/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001147/DRAFT","spec_version":"1.3.0","etag":"8df10254179af3af7b93b1eaf3c242e81d734817f0141c382bd0fe180a872dde","provenance_domain":{"version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-08-01T18:12:38.696Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) GlyGen-PDB Cross References dataset contains SARS-CoV-1 [taxid:694009] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"SARS-CoV-1","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":289,"last_update":"2024-08-01T18:12:38.696042Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001148/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001148/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Chicken GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The chicken GlyGen-PDB Cross References dataset contains Gallus gallus [taxid:9031] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_pdb_map.csv","filename":"chicken_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_pdb_map.stat.csv","filename":"chicken_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T01:01:22.105888Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001149/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001149/DRAFT","spec_version":"1.3.0","etag":"b8ba33e315e56f3d5c151466da04ce2f41b6009a614be7e0a9e2d2a71088793e","provenance_domain":{"name":"Dicty GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"2024-08-01T00:18:04","modified":"2024-07-31T17:06:55.479Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dicty GlyGen-PDB Cross References dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_pdb_map.csv","filename":"dicty_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_pdb_map.stat.csv","filename":"dicty_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-08-01T01:06:37.206997Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001150/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001150/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Rhea ID-EC mapping","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-08-01T12:24:01.237Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rhea ID-EC mapping contains Rhea IDs and their linked complete EC number. If you use this dataset please provide proper attribution to GlyGen and Rhea."],"description_domain":{"keywords":["EC number","Rhea","reactions","EC"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_reaction2ec_rhea.csv","filename":"protein_reaction2ec_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_reaction2ec_rhea.stat.csv","filename":"protein_reaction2ec_rhea.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea ID-EC mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"13d30c0a8a9d33c3d9f760336eae5d9412e745575e0dae4da0ac2b03489a858b"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":155,"last_update":"2024-08-01T12:24:01.237710Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001151/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001151/DRAFT","spec_version":"1.3.0","etag":"1bdcbca921219af75e69108104356681ebb9e05787ec185b0418cd0c37c1d094","provenance_domain":{"name":"Human Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:48:18","modified":"2024-12-05T16:16:44.558Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Predicted O-Glycosylation Sites dataset contains predicted Homo sapiens (TaxID: 9606) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"human_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":758,"last_update":"2024-12-05T16:16:44.558122Z","access_count":11},{"object_id":"https://biocomputeobject.org/GLY_001152/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001152/DRAFT","spec_version":"1.3.0","etag":"29e772fe1cb6e4f14d71a53f4ccf0fa09c92435390a53680face7680120d9a25","provenance_domain":{"name":"Pig Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:51:45","modified":"2024-12-05T16:18:55.533Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Predicted O-Glycosylation Sites dataset contains predicted Sus scrofa (TaxID: 9823) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"pig_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"pig_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":753,"last_update":"2024-12-05T16:18:55.533816Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001153/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001153/DRAFT","spec_version":"1.3.0","etag":"a085dfd0b0431eec8bb11f72f9abfa1cc713033578f4e81f0f856f8cde157a10","provenance_domain":{"name":"Mouse Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-05T16:09:36","modified":"2024-12-05T16:17:07.543Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Predicted O-Glycosylation Sites dataset contains predicted Mus musculus (TaxID: 10090) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"mouse_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":759,"last_update":"2024-12-05T16:17:07.543413Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001154/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001154/DRAFT","spec_version":"1.3.0","etag":"06273d54a7568baa7387e01e1a8718cd5e45fc3a9c5c75516e7305fa5f499df1","provenance_domain":{"name":"HCV1a Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:52:59","modified":"2024-12-05T16:25:35.119Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1a Predicted O-Glycosylation Sites dataset contains predicted Hepatitis C virus (isolate H77) (TaxID: 63746) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1a_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"hcv1a_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":782,"last_update":"2024-12-05T16:25:35.119468Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001155/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001155/DRAFT","spec_version":"1.3.0","etag":"12ef78f05957a22210d4634682f9450b62149af61881268e482b1426128ee5fa","provenance_domain":{"name":"HCV1b Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T17:57:04","modified":"2024-12-05T16:28:15.083Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1b Predicted O-Glycosylation Sites dataset contains predicted Hepatitis C virus (isolate Japanese) (TaxID: 11116) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path file path to the canonical protein sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"hcv1b_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"hcv1b_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"luke.johnson","authorized_users":null,"state":"DRAFT","score":788,"last_update":"2024-12-05T16:28:15.083222Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001156/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001156/DRAFT","spec_version":"1.3.0","etag":"74babe1083b11ce29d8517012a883fbe9424d201eac5aa170c296f8a1dbb16a0","provenance_domain":{"name":"Arabidopsis Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T17:47:21","modified":"2024-12-05T16:32:26.844Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Predicted O-Glycosylation Sites dataset contains predicted Arabidopsis thaliana (TaxID: 3702) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path file path to the canonical protein sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"arabidopsis_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"arabidopsis_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":775,"last_update":"2024-12-05T16:32:26.844103Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001157/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001157/DRAFT","spec_version":"1.3.0","etag":"c00f705974b5fee0f9d51a925bae6d53e850ea80942aa8c1d0cb01ab02610eab","provenance_domain":{"name":"Rat Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T16:50:43","modified":"2024-12-05T16:17:35.082Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Predicted O-Glycosylation Sites dataset contains predicted Rattus norvegicus (TaxID: 10116) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"rat_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":763,"last_update":"2024-12-05T16:17:35.082440Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001158/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001158/DRAFT","spec_version":"1.3.0","etag":"564199f4b67d131063e7ce297a138787bd5db2b6a47b4e86a536c3d7b403e0fc","provenance_domain":{"name":"SARS-CoV1 Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T16:50:43","modified":"2024-12-10T16:45:03.639Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV1 Predicted O-Glycosylation Sites dataset contains predicted Severe acute respiratory syndrome-related coronavirus (TaxID: 694009) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"sarscov1_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":815,"last_update":"2024-12-10T16:45:03.639686Z","access_count":21},{"object_id":"https://biocomputeobject.org/GLY_001159/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001159/DRAFT","spec_version":"1.3.0","etag":"8fb81c5e009a5574cb97fdfaa6ab0f20e86e029f5c3339408122975906d8af6b","provenance_domain":{"name":"SARS-CoV2 Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T16:50:43","modified":"2024-12-05T16:31:16.786Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV-2 Predicted O-Glycosylation Sites dataset contains predicted Severe acute respiratory syndrome coronavirus 2 (TaxID: 2697049) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"sarscov2_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":810,"last_update":"2024-12-05T16:31:16.786875Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001160/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001160/DRAFT","spec_version":"1.3.0","etag":"7ad7ec90acebccbd2eca07014d262edc3384908cda50c109a3c0f2aa18e3f3c3","provenance_domain":{"name":"Yeast Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-2.6.1","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T16:50:43","modified":"2025-03-04T16:37:43.864Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast predicted O-Glycosylation Sites dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions with information on reported and predicted O-Glycosylation sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"yeast_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"yeast_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2025-03-04T16:37:43.864752Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001161/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001161/DRAFT","spec_version":"1.3.0","etag":"54298e3e1eb17ac2c7f0cc3192e110d5523765038974f40343861577b7b1984d","provenance_domain":{"name":"Chicken Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T17:48:27","modified":"2024-12-05T16:15:47.038Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Predicted O-Glycosylation Sites dataset contains predicted Gallus gallus (TaxID: 9031) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path file path to the canonical protein sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"chicken_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"chicken_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":762,"last_update":"2024-12-05T16:15:47.038317Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001162/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001162/DRAFT","spec_version":"1.3.0","etag":"0397da8e2b2fadbcf08d4540df25e594b7a072961edaa8f08bf3d6fcb5437571","provenance_domain":{"name":"Dicty Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T17:49:29","modified":"2024-12-05T16:23:06.521Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Predicted O-Glycosylation Sites dataset contains predicted Dictyostelium discoideum (TaxID: 44689) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path file path to the canonical protein sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"dicty_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"dicty_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":774,"last_update":"2024-12-05T16:23:06.521604Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001163/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001163/DRAFT","spec_version":"1.3.0","etag":"96dd5332ce1e5bd7932bfb1f01aa851114df84acd52730c75924aca8d072fb10","provenance_domain":{"name":"Fruitfly Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T17:46:28","modified":"2024-12-05T16:20:52.673Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Predicted O-Glycosylation Sites dataset contains predicted Drosophila melanogaster (TaxID: 7227) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path file path to the canonical protein sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"input_subdomain":[{"uri":{"filename":"fruitfly_protein_canonicalsequences.fasta","uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"fruitfly_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":775,"last_update":"2024-12-05T16:20:52.673133Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001164/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001164/DRAFT","spec_version":"1.3.0","etag":"54e369894d2c9fbc528a37a375844fce323a5f375beacc259ebbb9da0b986b15","provenance_domain":{"name":"Human blood platelet Glycosylation Sites study citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-06T14:13:31","modified":"2024-08-06T14:16:52.156Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from the Human blood platelet Glycosylation Sites dataset file https://data.glygen.org/GLY_001051."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the canonical UniProt protein ac in the dataset to the origin publication."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_platelet.csv","filename":"human_proteoform_citations_glycosylation_sites_platelet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_platelet.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_platelet.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":174,"last_update":"2024-08-06T14:16:52.156207Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001165/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001165/DRAFT","spec_version":"1.3.0","etag":"b7e961698c02708df0c6b0248949057bb2481eb85fd96d5a620ea434dedaf531","provenance_domain":{"name":"Human Proteoform Glycosylation Citations (CarbBank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-10T21:03:16","modified":"2024-12-10T22:16:22.855Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Proteoform Glycosylation Citations (CarbBank) dataset contains Homo sapiens [taxid:9606] publication information of glycoproteins from the Human CarbBank Glycosylation Sites dataset (https://data.glygen.org/GLY_001113). The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from the CarbBank dataset. CarbBank was a pioneering database that cataloged carbohydrate structures and related biochemical information. Although no longer actively maintained, CarbBank laid the groundwork for modern glycoinformatics tools and databases, influencing subsequent efforts to document carbohydrate-related data systematically. Please cite GlyGen and CarbBank if you use this dataset. "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"human_proteoform_glycosylation_sites_carbbank.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_glycosylation_sites_carbbank.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_citations_glycosylation_sites_carbbank.csv","filename":"human_proteoform_citations_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/human_proteoform_citations_glycosylation_sites_carbbank.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (Carbbank)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":889,"last_update":"2024-12-10T22:16:22.855679Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001166/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001166/DRAFT","spec_version":"1.3.0","etag":"b60c2114cb5d6c4b74312a6282d6bfcb0fb17288fd9b239d91829f048d48a1db","provenance_domain":{"name":"Mouse Proteoform Glycosylation Citations (CarbBank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-10T21:03:46","modified":"2024-12-10T22:19:00.713Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Proteoform Glycosylation Citations (CarbBank) dataset contains Mus musculus [taxid:10090] publication information of glycoproteins from the Mouse CarbBank Glycosylation Sites dataset (https://data.glygen.org/GLY_001114). The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from the CarbBank dataset. CarbBank was a pioneering database that cataloged carbohydrate structures and related biochemical information. Although no longer actively maintained, CarbBank laid the groundwork for modern glycoinformatics tools and databases, influencing subsequent efforts to document carbohydrate-related data systematically. Please cite GlyGen and CarbBank if you use this dataset. "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"mouse_proteoform_glycosylation_sites_carbbank.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_glycosylation_sites_carbbank.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_citations_glycosylation_sites_carbbank.csv","filename":"mouse_proteoform_citations_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/mouse_proteoform_citations_glycosylation_sites_carbbank.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (Carbbank)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":890,"last_update":"2024-12-10T22:19:00.713642Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001167/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001167/DRAFT","spec_version":"1.3.0","etag":"ba358709e8034dc049ba6070ebfa5e84caaf1fc4bb27f30d6512a3c8732d3b95","provenance_domain":{"name":"Yeast Proteoform Glycosylation Citations (CarbBank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-10T21:04:09","modified":"2024-12-10T22:21:01.184Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Proteoform Glycosylation Citations (CarbBank) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] publication information of glycoproteins from the Yeast CarbBank Glycosylation Sites dataset (https://data.glygen.org/GLY_001116). The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from the CarbBank dataset. CarbBank was a pioneering database that cataloged carbohydrate structures and related biochemical information. Although no longer actively maintained, CarbBank laid the groundwork for modern glycoinformatics tools and databases, influencing subsequent efforts to document carbohydrate-related data systematically. Please cite GlyGen and CarbBank if you use this dataset. "],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"yeast_proteoform_glycosylation_sites_carbbank.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/yeast_proteoform_glycosylation_sites_carbbank.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/yeast_proteoform_citations_glycosylation_sites_carbbank.csv","filename":"yeast_proteoform_citations_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/yeast_proteoform_citations_glycosylation_sites_carbbank.stat.csv","filename":"yeast_proteoform_citations_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (Carbbank)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":913,"last_update":"2024-12-10T22:21:01.184073Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001168/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001168/DRAFT","spec_version":"1.3.0","etag":"49b62cd0e2aae8dd65ad1be89ce84b07e098e42dc2b882061a58bbc9685a6049","provenance_domain":{"name":"Rat Proteoform O-GlcNAc Glycosylation Citations (Carbbank)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-25T20:55:04","modified":"2024-10-25T20:55:27.544Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMIDs from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset"}],"keywords":["glycosylation","reported glycosylation","Carbbank"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"rat_proteoform_glycosylation_sites_carbbank.csv","uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_glycosylation_sites_carbbank.csv"}}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_citations_glycosylation_sites_carbbank.csv","filename":"rat_proteoform_citations_glycosylation_sites_carbbank.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/rat_proteoform_citations_glycosylation_sites_carbbank.stat.csv","filename":"rat_proteoform_citations_glycosylation_sites_carbbank.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (Carbbank)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T20:55:27.544653Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001169/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001169/DRAFT","etag":"7a36bb4efb214e18c1c16d4a80d727dc","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Xref Metabolomics Workbench","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:55:11.149043","modified":"2024-05-17T11:23:55.326Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides cross-references to Metabolomics Workbench ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.metabolomicsworkbench.org/"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Metabolomics Workbench cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Metabolomics Workbench","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_mw.csv","filename":"glycan_xref_mw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_mw.stat.csv","filename":"glycan_xref_mw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-09-12T16:02:41.445160Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001170/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001170/DRAFT","etag":"7a36bb4efb214e18c1c16d4a80d727dc","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Xref Metabolomics Workbench","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:55:11.149043","modified":"2024-05-17T11:23:55.326Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides cross-references to Metabolomics Workbench ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.metabolomicsworkbench.org/"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Metabolomics Workbench cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Metabolomics Workbench","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_mw.csv","filename":"glycan_xref_mw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_mw.stat.csv","filename":"glycan_xref_mw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-09-12T16:07:18.403259Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001171/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001171/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"5c1a57d0006bac59f004c5eefab87b6ca7dd111bc8067880fbbbcf01edec5918","provenance_domain":{"name":"Bovine O-GlcNAc Glycosylation Sites (MCW)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:53:24.527843","modified":"2024-12-05T18:50:36.914Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine O-GlcNAc Glycosylation Sites (MCW) contains Bos taurus (taxid:9913) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s bovine protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to bovine species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding bovine UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-proteoform-dataset.py","description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"bovine_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"bovine_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":2965,"last_update":"2024-12-05T18:50:36.914432Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001172/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001172/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"774a5002928b8ffe109cbe76dd341f28f71558bf68d2665af5b7ddcafa9921df","provenance_domain":{"name":"Bovine O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-24T16:22:06.506Z","modified":"2024-12-03T18:27:31.860Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","contribution":["contributedBy"],"affiliation":"Georgetown University Medical Center, Georgetown University","email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains Bos taurus (taxid:9913) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. "}],"keywords":[null,"O-GlcNAc","Serine"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_oglcnac_atlas.csv","filename":"bovine_proteoform_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"bovine_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":343,"last_update":"2024-12-03T18:27:31.860432Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001173/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001173/DRAFT","spec_version":"1.3.0","etag":"b2b95ccf06e12501a2f46c57f4846f2d0296a44fd6163e25eafd36bf5b097e17","provenance_domain":{"name":"Bovine Glycation Sites (UniProtKB)","version":"v-x.x.x","created":"2020-08-17T17:02:18.395740","modified":"2024-12-10T20:13:04.456Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycation Sites (UniProtKB) dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions with information on reported and predicted glycation sites from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"keywords":["UniProtKB","PubMed","Evidence and conclusion Ontology","glycation","reported glycation ","predicted glycation ","glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycation information from the triplestore containing triples from the nt file and extracts as a csv dataset. "}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycation_sites_uniprotkb.csv","filename":"bovine_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"bovine_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/","filename":"make-proteoform-dataset.py"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":353,"last_update":"2024-12-10T20:13:04.456516Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001174/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001174/DRAFT","etag":"20b543c23d79aafdbe27cc620c13e541","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Proteoform Glycosylation Citations (UniProtKB)","version":"v-x.x.x","created":"2021-06-03T16:32:02.053252","modified":"2024-05-17T11:24:04.661Z","contributors":[{"name":"Jeet Vora","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Proteoform Glycosylation Citations (UniProtKB) dataset contains Bos taurus [taxid:9913] citation details of the publications present in the dataset Bovine Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000038)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"bovine_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"bovine_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}],"input_subdomain":[{}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T18:47:39.760109Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001175/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001175/DRAFT","etag":"3a974abf8206bcfb5d15d47e25a980dc","spec_version":"1.3.0","provenance_domain":{"name":"Bovine O-GlcNAc Glycosylation Citations (MCW)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-07-15T16:28:21.779974","modified":"2024-05-17T11:24:03.245Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Bovine O-GlcNAc Glycosylation Sites (MCW)  https://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"bovine_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"bovine_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T18:53:20.412232Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001176/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001176/DRAFT","spec_version":"1.3.0","etag":"19aafc73feebe71da86f1f25e4d483a95eaf2b32d6385e8336c9c340db58722a","provenance_domain":{"name":"Bovine Glycosylation Sites (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.909814","modified":"2026-08-19T10:01:51.658Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jasmine Young","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"jasmine@rcsb.rutgers.edu"},{"name":"Chenghua Shao","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"chenghua@rcsb.rutgers.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycosylation Sites (RCSB PDB) dataset contains Bos taurus [taxid:9913] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"input_list":[]}],"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_pdb.csv","filename":"bovine_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_pdb.stat.csv","filename":"bovine_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":506,"last_update":"2026-08-19T10:01:51.658951Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001177/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001177/DRAFT","etag":"a6e4dc8e673299311ef1c2a2162ed790","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Proteoform Citations (GlyConnect)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-04-28T10:49:06.505148","modified":"2024-05-17T11:24:02.257Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"bovine_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"bovine_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T19:03:28.945698Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001178/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001178/DRAFT","spec_version":"1.3.0","etag":"a207f976192260c5f289d0c606234737a4eccd58cb5857f2c5049b80a4bd7f0f","provenance_domain":{"name":"Bovine Phosphorylation Sites (iPTMNet)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-08-17T16:43:14.212000","modified":"2024-12-01T23:37:18.421Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Phosphorylation Sites (iPTMNet) dataset contains Bos taurus [taxid:9913] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","input_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_phosphorylation_sites_iptmnet.csv","filename":"bovine_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"bovine_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":355,"last_update":"2024-12-01T23:37:18.421558Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001179/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001179/DRAFT","etag":"a7a9fc1c226fdd1f365d154fd051071e","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Phosphorylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-09-06T14:06:39.000407","modified":"2024-05-17T11:23:54.582Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Phosphorylation Sites (UniProtKB) dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"io_domain":{"input_subdomain":[{}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"bovine_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"bovine_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T19:13:51.034317Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001180/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001180/DRAFT","spec_version":"1.3.0","etag":"432daf9e3858f0b5667237b46909186f4f023d81ca711daa5574f10a97c5b9ac","provenance_domain":{"name":"Bovine Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.905721","modified":"2024-12-10T17:02:23.423Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycosylation Sites (UniProtKB) dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Bos taurus proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_uniprotkb.csv","filename":"bovine_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"bovine_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":330,"last_update":"2024-12-10T17:02:23.423615Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001181/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001181/DRAFT","etag":"dc030b410992c24706d70002578dadba","spec_version":"1.3.0","provenance_domain":{"name":"Bovine O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-02-27T21:08:01.227Z","modified":"2024-05-17T11:24:10.298Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jungfeng Ma","orcid":"","affiliation":"Georgetown University Medical Center, Georgetown University","contribution":["contributedBy"],"email":"junfeng.ma@georgetown.edu "},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Bovine O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)  https://data.glygen.org/GLY_000708, contributed by Jungfeng Ma's group."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (O-GlcNAc Atlas)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{}],"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv","filename":"bovine_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv","filename":"bovine_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv"}}]}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T19:23:59.571712Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001182/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001182/DRAFT","etag":"8d51841cd719647153cd66e39dd20f46","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Glycosylation Sites (GlyConnect) ","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2020-02-10T10:16:50.152756","modified":"2024-05-17T11:23:56.452Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycosylation Sites (GlyConnect) dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Bos taurus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (bovine_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_glyconnect.csv","filename":"bovine_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"bovine_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-25T19:28:55.545841Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001183/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001183/DRAFT","spec_version":"1.3.0","etag":"93371c32a4be94a99e134e351f0c06e0a3d6a176f4b0bd1a0d714926a32ee095","provenance_domain":{"name":"Bovine Proteoform Phosphorylation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-10-15T08:00:04.645468","modified":"2025-10-09T14:48:23.947Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Proteoform Phosphorylation Citations (UniProtKB) dataset contains Bos taurus [taxid:9913] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"bovine_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"bovine_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":343,"last_update":"2025-10-09T14:48:23.947046Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001184/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001184/DRAFT","spec_version":"1.3.0","etag":"0d2e77f84adcb6b86524dba5859e989bb23add143fea58d8e973477005217c22","provenance_domain":{"name":"Bovine Proteoform Phosphorylation Citations (iPTMnet)","version":"v-x.x.x","created":"2021-06-03T17:29:17.656153","modified":"2024-12-05T19:42:09.782Z","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Proteoform Citations (iPTMNet) contains Bos taurus [taxid:9913] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"bovine_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"bovine_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":416,"last_update":"2024-12-05T19:42:09.782011Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001185/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001185/DRAFT","spec_version":"1.3.0","etag":"974ab877d451484516bb1e7dfa19a774178a136e5b5e46d9b820e9cb7a8a6806","provenance_domain":{"name":"Bovine Proteoform Glycation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2021-06-04T12:34:52.072705","modified":"2024-12-10T17:03:34.206Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Proteoform Glycation Citations (UniProtKB) dataset contains Bos taurus [taxid:9913] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs","input_list":[]}],"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycation_sites_uniprotkb.csv","filename":"bovine_proteoform_citations_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycation_sites_uniprotkb.stat.csv","filename":"bovine_proteoform_citations_glycation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Citations (UniProtKB)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":336,"last_update":"2024-12-10T17:03:34.206621Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001186/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001186/DRAFT","etag":"1e63e95a29c670e3f834e17de13f4c76","spec_version":"1.3.0","provenance_domain":{"name":"Metabolomics Workbench Crossreferences Mapping","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-03-29T12:16:21.978852","modified":"2024-05-17T11:24:07.070Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":[],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Metabolomics Workbench Crossreferences","category_name":"tag"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Metabolomics","Workbench","GlyGen","crossreferences"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"input_subdomain":[{}],"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_glygen_mw_xref_mapping.tsv","filename":"glycan_glygen_mw_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_glygen_mw_xref_mapping.stat.csv","filename":"glycan_glygen_mw_xref_mapping.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-28T17:30:20.885834Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001187/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001187/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-10-30T16:52:09.241Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Isoform sequences (UniProtKB) dataset contains Bos taurus [taxid:9913] protein fasta sequences for the bovine isoform accessions from the UniProtKB database."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all bovine isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}],"keywords":["protein isoform sequences","fasta","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_allsequences.fasta","filename":"bovine_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_allsequences.stat.csv","filename":"bovine_protein_allsequences.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"e63261272e5321b6662ce83f7daa5af775dc0880568915fb426140150874e851"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":216,"last_update":"2024-10-30T16:52:09.241955Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001188/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001188/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-30T16:59:51","modified":"2024-10-30T17:09:33.103Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Bovine Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Bos taurus [taxid:9913] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_altnames.csv","filename":"bovine_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_altnames.stat.csv","filename":"bovine_protein_altnames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"ee4a963b3c9598e5ebf73fa997bf41f2fdc6454329a97aaf21a96799a168178f"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":270,"last_update":"2024-10-30T17:09:33.103147Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001189/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001189/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Binary Interactions (IntAct)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Binary Interaction (IntAct) dataset contains Bos taurus [taxid:9913] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc.  If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","input_list":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_binary_interactions.csv","filename":"bovine_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_binary_interactions.stat.csv","filename":"bovine_protein_binary_interactions.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-gallus-gallus.nt"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-30T17:04:34.781247Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001190/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001190/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-30T17:14:33","modified":"2024-10-30T17:22:29.807Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Canonical (UniProtKB) Sequences dataset contains Bos taurus [taxid:9913] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all bovine canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}],"keywords":["protein sequence","fasta","UniProtKB canonical accessions"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_canonicalsequences.fasta","filename":"bovine_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_canonicalsequences.stat.csv","filename":"bovine_protein_canonicalsequences.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"ab53f71c8e971a9f697019fd39e46246d9e1f2be58d7a8832ec3095f1e66f77c"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":299,"last_update":"2024-10-30T17:22:29.807201Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001191/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001191/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-30T17:22:43","modified":"2024-10-30T17:23:54.714Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Bovine Protein Citations dataset contains publication information for Bos taurus [taxid:9913] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}],"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_uniprotkb.csv","filename":"bovine_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_uniprotkb.stat.csv","filename":"bovine_protein_citations_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"3d7f2f243bab7b49014cb47d9ab4aa3cc04ad52c24fa73c8a70caeb645bdf7cf"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":503,"last_update":"2024-10-30T17:23:54.714471Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001192/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001192/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Enzyme Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-30T17:32:32","modified":"2024-10-30T17:33:46.193Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Enzyme Annotation (UniProtKB) dataset contains Bos taurus [taxid:9913] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}],"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_enzyme_annotation_uniprotkb.csv","filename":"bovine_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"bovine_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"c7b57fa143f378842f00e686976e26d3eb7b7ad25bb9d0af95ac15786a4b8fef"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":384,"last_update":"2024-10-30T17:33:46.193262Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001193/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001193/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Function (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-30T17:49:32","modified":"2024-10-30T17:50:52.644Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Function (UniProtKB) dataset contains biological function annotation for Bos taurus [taxid:9913] protein accessions from the UniProtKB database.  If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein function","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_function_uniprotkb.csv","filename":"bovine_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_function_uniprotkb.stat.csv","filename":"bovine_protein_function_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"fe9743020101a35718c3bd22a5a8efe6211f0f5cae36aec12af4a27d24cb1922"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":312,"last_update":"2024-10-30T17:50:52.644806Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001194/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001194/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Gene Locus (Ensembl)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-10-30T18:34:34.092Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Gene Locus (Ensembl) contains Bos taurus [taxid:9913] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_genelocus.csv","filename":"bovine_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_genelocus.stat.csv","filename":"bovine_protein_genelocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"8cf9b4de7476d9cb0f27fb25b4f691953175e9d42a119f12551dc5fe45e79611"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":377,"last_update":"2024-10-30T18:34:34.092666Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001195/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001195/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Gene Symbols (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-30T18:40:06","modified":"2024-10-30T18:41:24.356Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Bovine Gene Symbols (NCBI RefSeq) dataset contains Bos taurus [taxid:9913] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_genenames_refseq.csv","filename":"bovine_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_genenames_refseq.stat.csv","filename":"bovine_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"7a56f15d6e2e23d16f50be468ab574419c2b5d452c6654bf86ee43ee2d50e9df"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":301,"last_update":"2024-10-30T18:41:24.356384Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001196/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001196/DRAFT","etag":"","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Bos taurus [taxid:9913] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_04_08/uniprot-proteome-gallus-gallus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_genenames_uniprotkb.csv","filename":"bovine_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_genenames_uniprotkb.stat.csv","filename":"bovine_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-30T18:46:03.006116Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001197/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001197/DRAFT","spec_version":"1.3.0","etag":"1b4f9b3fcdc88a3c92181ad04a2040a793ec03701dc8535b203bc46b14b88b0b","provenance_domain":{"name":"Bovine UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-10-31T15:24:31","modified":"2024-10-31T15:24:35.648Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref AlphaFold contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_alphafolddb.csv","filename":"bovine_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_alphafolddb.stat.csv","filename":"bovine_protein_xref_alphafolddb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":450,"last_update":"2024-10-31T15:24:35.648702Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001198/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001198/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine UniProtKB Xref O-GlcNAc (MCW)","version":"v-x.x.x","license":"httpss://creativecommons.org/licenses/by/4.0/","modified":"2024-10-31T15:24:03.781Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref O-GlcNAc (MCW) contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers.  If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O-GlcNAc(MCW) is a database for O-GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","input_list":[]}],"keywords":["Bovine","O-GlcNAc (MCW)","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_oglcnac_mcw.csv","filename":"bovine_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_oglcnac_mcw.stat.csv","filename":"bovine_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAc (MCW) cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"1ae3b77ae22bff324dad9bc39fadca4198929316085fb38891ecbfdc76ea0740"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":434,"last_update":"2024-10-31T15:24:03.781603Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001199/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001199/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","modified":"2024-10-31T15:33:01.404Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine GlyGen-PDB Cross References dataset contains Bos taurus [taxid:9913] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset."}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_pdb_map.csv","filename":"bovine_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_pdb_map.stat.csv","filename":"bovine_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"7dae68de15dcaf97b552730dff5e27fefafcb3f5c21ed6d4c9f548d6dcc13057"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":321,"last_update":"2024-10-31T15:33:01.404691Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001200/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001200/DRAFT","spec_version":"1.3.0","etag":"","provenance_domain":{"name":"Bovine UniProtKB Xref Pfam","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref Pfam contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein family","Pfam","cross-reference"]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-sus-scrofa.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-sus-scrofa.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pfam.csv","filename":"bovine_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pfam.stat.csv","filename":"bovine_protein_xref_pfam.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2024-10-31T15:43:10.600222Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001201/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001201/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"name":"Bovine N-Glycosylation Sequon","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-10-31T16:03:00.041Z"},"usability_domain":["The Bovine N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Bos taurus [taxid:9913] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. "],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","input_list":[]}],"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_glycosylation_motifs.csv","filename":"bovine_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_glycosylation_motifs.stat.csv","filename":"bovine_protein_glycosylation_motifs.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"b6606ef4ef87cd0ef64f190a165d1aecfa1e63be9e6ec55253c6ed6f130d58b4"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":409,"last_update":"2024-10-31T16:03:00.041119Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001202/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001202/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine UniProtKB Xref PRO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-10-31T16:20:47.597Z"},"usability_domain":["The Bovine UniprotKB Xref PRO contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["protein ontology","PRO","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pro.csv","filename":"bovine_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pro.stat.csv","filename":"bovine_protein_xref_pro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PRO cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{},"etag":"9bc6ee35b0cebcbc5fe0835d9e9ee320656959e87aed866d9250ab3befeb079f"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":467,"last_update":"2024-10-31T16:20:47.597268Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001203/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001203/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Reactions (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-10-31T16:56:03.637Z"},"usability_domain":["The Bovine Protein Reactions (Reactome) dataset contains reactions information for pathways for Bos taurus [taxid:9913] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","input_list":[]}],"keywords":["Reactome","Pathway","Reactions","PMID"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_reactions_reactome.csv","filename":"bovine_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_reactions_reactome.stat.csv","filename":"bovine_protein_reactions_reactome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{},"etag":"221b5051031ad1e2cc9ea1e3e8bc0bdc0c87404d03970e2a3a30eb2ec5de3f98"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":397,"last_update":"2024-10-31T16:56:03.637315Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001204/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001204/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Protein Names (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-10-31T17:09:54.149Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Names (NCBI RefSeq) dataset contains Bos taurus [taxid:9913] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_proteinnames_refseq.csv","filename":"bovine_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_proteinnames_refseq.stat.csv","filename":"bovine_protein_proteinnames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"7b5870cc1cb89e1a183ebb51a924e85a4811ce83d965b7444936e4e36b089956"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":314,"last_update":"2024-10-31T17:09:54.149168Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001205/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001205/DRAFT","spec_version":"1.3.0","provenance_domain":{"name":"Bovine UniProtKB Xref CAZy","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-10-31T17:20:34.319Z"},"usability_domain":["The Bovine UniprotKB Xref CAZy contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_cazy.csv","filename":"bovine_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_cazy.stat.csv","filename":"bovine_protein_xref_cazy.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"05a035f1c00268e7f471f63ef2048d8878cc5dc138f539e67c8e594511afb1f7"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":563,"last_update":"2024-10-31T17:20:34.319811Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001206/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001206/DRAFT","provenance_domain":{"name":"Bovine Protein Site Annotation","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-10-31T19:53:28.725Z"},"usability_domain":["The Bovine Protein Site Annotation (UniProtKB) dataset contains Bos taurus [taxid:9913] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}],"keywords":["site annotation","amino acid range","UniProtKB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_site_annotation_uniprotkb.csv","filename":"bovine_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_site_annotation_uniprotkb.stat.csv","filename":"bovine_protein_site_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{},"etag":"5b9266e2192309e7b2a762c3e2f8a94caea0483d6cdb5386d57273c05bbb0cf2"},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":377,"last_update":"2024-10-31T19:53:28.725623Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001207/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001207/DRAFT","spec_version":"1.3.0","etag":"73544ccb8b96044dc48a86974223b44929b3e18d24a942f4e1674a1a8da85d08","provenance_domain":{"name":"Bovine UniProtKB Xref OMA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-10-31T20:02:13.138Z"},"usability_domain":["The Bovine UniProtKB Xref OMA contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["orthologs","OMA","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_oma.csv","filename":"bovine_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_oma.stat.csv","filename":"bovine_protein_xref_oma.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"OMA cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":435,"last_update":"2024-10-31T20:02:13.138271Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001208/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001208/DRAFT","spec_version":"1.3.0","etag":"fb1a7558b8048294ba3a8cff7573a08432c95b6434e791593969923dc38f2cb7","provenance_domain":{"name":"Bovine Pathways (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"derived_from":[],"review":[]},"usability_domain":["REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["pathways","reactions","REACTOME"]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_pathways_reactome.csv","filename":"bovine_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_pathways_reactome.stat.csv","filename":"bovine_protein_pathways_reactome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":115,"last_update":"2024-10-31T20:10:22.248439Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001209/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001209/DRAFT","spec_version":"1.3.0","etag":"d9f816cdcee67c8e9d3dac63fc893476f8370fec77b0600741ec595283b03133","provenance_domain":{"name":"Bovine UniProtKB Xref BRENDA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-11-01T11:27:20.596Z"},"usability_domain":["The Bovine UniprotKB Xref BRENDA contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["enzyme","ec number","BRENDA","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_brenda.csv","filename":"bovine_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_brenda.stat.csv","filename":"bovine_protein_xref_brenda.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":576,"last_update":"2024-11-01T11:27:20.596388Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001210/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001210/DRAFT","spec_version":"1.3.0","etag":"2db91e45ad5c5ec5f3413a214759b0856123b04578771d70a94b62f95567a0a0","provenance_domain":{"name":"Bovine UniProtKB Xref PANTHER","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2024-11-01T11:37:23.944Z"},"usability_domain":["The Bovine UniProtKB Xref PANTHER contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["protein family","PANTHER","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_panther.csv","filename":"bovine_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_panther.stat.csv","filename":"bovine_protein_xref_panther.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PANTHER cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":561,"last_update":"2024-11-01T11:37:23.944048Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001211/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001211/DRAFT","spec_version":"1.3.0","etag":"3e7e979d11b9c2c1ce5194301d17dc5033ea30b3bdbda5d852c9cbbda9b28dd8","provenance_domain":{"name":"Bovine UniProtKB Xref KEGG PATHWAY","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"derived_from":[],"review":[]},"usability_domain":["The Bovine UniProtKB Xref KEGG PATHWAY contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen, KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["pathways","reactions","KEGG Pathway","cross-reference"]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_kegg.csv","filename":"bovine_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_kegg.stat.csv","filename":"bovine_protein_xref_kegg.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"KEGG Pathway cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":495,"last_update":"2024-11-01T11:44:50.603215Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001212/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001212/DRAFT","spec_version":"1.3.0","etag":"2c03c3f5f8ec5eec000910bca7a4616c3e1540fa6189c1581c70050f24b53d0a","provenance_domain":{"name":"Bovine NCBI Protein Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-01T12:09:33.531Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine NCBI Protein Linkouts contains Bos taurus [taxid:9913] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}],"keywords":["NCBI Protein Linkouts","RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_ncbi_linkouts.csv","filename":"bovine_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_ncbi_linkouts.stat.csv","filename":"bovine_protein_ncbi_linkouts.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":306,"last_update":"2024-11-01T12:09:33.531524Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001213/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001213/DRAFT","spec_version":"1.3.0","etag":"f1c04dfd6d1091465f9384a222a2ba55138f89ad80f28ca8f27c897458721e53","provenance_domain":{"name":"Bovine EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-03-04T15:47:10","modified":"2025-03-04T15:48:08.493Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine EBI-UniProtKB NT file contains proteome data for Bos taurus [taxid:9913] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}],"keywords":["NT","proteome","EMBL-EBI"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_ntdata.nt","filename":"bovine_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_ntdata.stat.csv","filename":"bovine_protein_ntdata.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":329,"last_update":"2025-03-04T15:48:08.493373Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001214/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001214/DRAFT","spec_version":"1.3.0","etag":"be6997151f2960a2dc4d0a6d86d2ed95a8279215c99581be49149325fe238d16","provenance_domain":{"name":"Bovine Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-01T12:42:41.980Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Not Applicable","contribution":["contributedBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Information (NCBI RefSeq) dataset contains Bos taurus [taxid:9913] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}],"keywords":["protein information","protein length","NCBI RefSeq","protein summary"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_info_refseq.csv","filename":"bovine_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_info_refseq.stat.csv","filename":"bovine_protein_info_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":349,"last_update":"2024-11-01T12:42:41.980668Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001215/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001215/DRAFT","spec_version":"1.3.0","etag":"186ad537404f641743fd56e73acf35db2e60260e7f64b22eed45132189d73472","provenance_domain":{"name":"Protein Resource Ontology [Bovine]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Darren Natale","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"dan5@georgetown.edu"},{"name":"Matthew Campbell ","affiliation":"UniCarbKB","contribution":["contributedBy"],"email":"m.campbell2@griffith.edu.au"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for Bos taurus [taxid:9913] proteins."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}],"keywords":["Proteoforms","PRO","UniCarbKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_pro_annotation.csv","filename":"bovine_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_pro_annotation.stat.csv","filename":"bovine_protein_pro_annotation.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":285,"last_update":"2024-11-01T12:58:27.156694Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001216/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001216/DRAFT","spec_version":"1.3.0","etag":"4c7b739be5cb6869424b3e7a2cfb9ca55451df88e2c6d792f1a0acc7eea0fc1e","provenance_domain":{"name":"Bovine Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:48:18","modified":"2024-12-05T16:34:20.546Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Predicted O-Glycosylation Sites dataset contains predicted Bos taurus (TaxID: 9913) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"bovine_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}},{"uri":{"filename":"combine_csv.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":757,"last_update":"2024-12-05T16:34:20.546613Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001217/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001217/DRAFT","spec_version":"1.3.0","etag":"9f5ec95b7c0cb842b5a44ddb31abb09792adf3e0fba5ac82cb63b452a6449508","provenance_domain":{"name":"Bovine UniProtKB Xref IntAct","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-11-04T15:58:07","modified":"2024-11-04T15:59:16.642Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Bovine UniProtKB Xref IntAct dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_intact.csv","filename":"bovine_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_intact.stat.csv","filename":"bovine_protein_xref_intact.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":638,"last_update":"2024-11-04T15:59:16.642379Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001218/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001218/DRAFT","spec_version":"1.3.0","etag":"6dbdafd1345273ed47ba2df47e14da4c1e3f8f21fb611b3e2ae70cbad8bddf05","provenance_domain":{"name":"Bovine Reaction Participants (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-11-04T16:13:01","modified":"2024-11-04T16:15:22.305Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Bos taurus [taxid:9913] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}],"keywords":["Reactome","Participant"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_participants_reactome.csv","filename":"bovine_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_participants_reactome.stat.csv","filename":"bovine_protein_participants_reactome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":450,"last_update":"2024-11-04T16:15:22.305265Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001219/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001219/DRAFT","spec_version":"1.3.0","etag":"2e10507426b535204767c1ee72796ba29ffffe7a78077552b8eac99836534106","provenance_domain":{"name":"Bovine Protein PTM Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-04T17:07:32.504Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein PTM Annotation (UniProtKB) dataset contains Bos taurus [taxid:9913] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format"}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_ptm_annotation_uniprotkb.csv","filename":"bovine_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_ptm_annotation_uniprotkb.stat.csv","filename":"bovine_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":377,"last_update":"2024-11-04T17:07:32.504478Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001220/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001220/DRAFT","spec_version":"1.3.0","etag":"5338333734941bbf2a3cab5a4b88239f6d49d4ce14b7212d38ce4275625241f2","provenance_domain":{"name":"Bovine UniProtKB Xref (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-11-04T17:13:26","modified":"2024-11-04T17:14:04.681Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref (UniProtKB) dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to UniProtKB database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_uniprotkb.csv","filename":"bovine_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_uniprotkb.stat.csv","filename":"bovine_protein_xref_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":307,"last_update":"2024-11-04T17:14:04.681371Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001221/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001221/DRAFT","etag":"e1e927405d1dfcb186da2b80d52d6321a67e454cfdf4266dfb9b7f5cda519498","spec_version":"1.3.0","provenance_domain":{"name":"Bovine UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniprotKB Xref RefSeq contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_refseq.csv","filename":"bovine_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_refseq.stat.csv","filename":"bovine_protein_xref_refseq.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"uniprot-proteome-gallus-gallus.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2024_06_20/uniprot-proteome-gallus-gallus.nt"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":765,"last_update":"2024-11-04T19:34:31.478221Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001222/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001222/DRAFT","spec_version":"1.3.0","etag":"4a889c51a6871e2355e50b93a7dae0de5e4a0a7a029ad18510c76bc4a8469dac","provenance_domain":{"name":"Bovine UniProtKB Xref NCBI Gene","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-08T19:02:25.005Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref NCBI Gene dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["gene id","NCBI gene","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_geneid.csv","filename":"bovine_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_geneid.stat.csv","filename":"bovine_protein_xref_geneid.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":609,"last_update":"2024-11-08T19:02:25.005138Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001223/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001223/DRAFT","spec_version":"1.3.0","etag":"824abffea774994cab744fa33e0c4642f0d3d89669a76577c06dc1cae00c14f8","provenance_domain":{"name":"Bovine Protein Sequence Info (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T13:19:24.721Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Sequence Info (UniProtKB) dataset contains Bos taurus [taxid:9913] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB sequence for all pig isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}],"keywords":["protein sequence info","fasta header","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_sequenceinfo.csv","filename":"bovine_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_sequenceinfo.stat.csv","filename":"bovine_protein_sequenceinfo.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":330,"last_update":"2024-11-11T13:19:24.721527Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001224/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001224/DRAFT","spec_version":"1.3.0","etag":"c99e0697fa75500d82ae833a5945757251e880cd921be7c029a3b42d98c3df32","provenance_domain":{"name":"Bovine UniProtKB xref GlyConnect","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T13:21:10.028Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Bovine UniProtKB xref GlyConnect dataset contains Bos taurus (taxid:9913) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_glyconnect.csv","filename":"bovine_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_glyconnect.stat.csv","filename":"bovine_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":165,"last_update":"2024-11-11T13:21:10.028892Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001225/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001225/DRAFT","spec_version":"1.3.0","etag":"fa1c5f4b2e6c83a9439b3ce78a92c5a64f3f1f4df0a5d6521ff0c78cde231b02","provenance_domain":{"name":"Bovine Reaction Participants (Rhea)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T14:28:26.953Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for Bos taurus [taxid:9913] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[]}],"keywords":["Rhea","Participants","Reactions"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_participants_rhea.csv","filename":"bovine_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_participants_rhea.stat.csv","filename":"bovine_protein_participants_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":435,"last_update":"2024-11-11T14:28:26.953098Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001226/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001226/DRAFT","spec_version":"1.3.0","etag":"5a885786bafa0ec19efd8a2cf5bc3557138e62dfc9ff02dfdbe405a102f226e1","provenance_domain":{"name":"Bovine Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T14:33:31.206Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Gene Ontology (GO) dataset contains Bos taurus [taxid:9913] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}],"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_go_annotation.csv","filename":"bovine_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_go_annotation.stat.csv","filename":"bovine_protein_go_annotation.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":318,"last_update":"2024-11-11T14:33:31.206376Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001227/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001227/DRAFT","spec_version":"1.3.0","etag":"94a4a83f1b095282506b96d1db22029023c3f0df5de229e3c9ae597135094445","provenance_domain":{"name":"Bovine UniprotKB Xref O-GlcNAcAtlas","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-12-03T18:24:03","modified":"2024-12-03T18:26:25.330Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniprotKB Xref O-GlcNAcAtlas dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to O-GlcNAcAtlas database accessions/identifiers. If you use this dataset please provide proper attribution to O-GlcNAcAtlas and GlyGen. O-GlcNAcAtlas is a a rigorously curated database for experimentally identified O-GlcNAc sites/proteins (https://oglcnac.org/atlas/)"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAcAtlas database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["Cross-references","O-GlcNAcAtlas"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_oglcnac_atlas.csv","filename":"bovine_protein_xref_oglcnac_atlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_oglcnac_atlas.stat.csv","filename":"bovine_protein_xref_oglcnac_atlas.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"O-GlcNAcAtlas cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":481,"last_update":"2024-12-03T18:26:25.330921Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001228/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001228/DRAFT","spec_version":"1.3.0","etag":"82e0afda5f6f6d05fa0ee4781e47d23cdef5000f2f276160dbf8fde58234695d","provenance_domain":{"name":"Bovine UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T15:08:56.236Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref PDB contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["protein 3D structure","RCSB PDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pdb.csv","filename":"bovine_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pdb.stat.csv","filename":"bovine_protein_xref_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":468,"last_update":"2024-11-11T15:08:56.236655Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001229/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001229/DRAFT","spec_version":"1.3.0","etag":"aba55e5eb225c8ff91656b9b5bbe651491ec798d796b94effb518ce47e276172","provenance_domain":{"name":"Bovine Transcript Locus (Ensembl Transcript coordinates)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-12-10T14:36:53.264Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Transcript Locus (Ensembl Transcript coordinates) contains UniProtKB Bos taurus [taxid:9913] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset.","input_list":[]}],"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_transcriptlocus.csv","filename":"bovine_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_transcriptlocus.stat.csv","filename":"bovine_protein_transcriptlocus.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":465,"last_update":"2024-12-10T14:36:53.264257Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001230/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001230/DRAFT","spec_version":"1.3.0","etag":"53283b81a8942dfffc51495a71b2af99bd75ec3a5b0f2862dd5e121a1eec756b","provenance_domain":{"name":"Bovine Glycohydrolases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T15:49:59.705Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycohydrolases dataset contains a list of Bos taurus [taxid:9913] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_glycohydrolase.csv","filename":"bovine_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_glycohydrolase.stat.csv","filename":"bovine_protein_glycohydrolase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":347,"last_update":"2024-11-11T15:49:59.705478Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001231/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001231/DRAFT","spec_version":"1.3.0","etag":"f398c140e4355075b0b8df5bf5dad2cbe988d7141a620e2f2f919cfd894d43c5","provenance_domain":{"name":"Bovine Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T15:58:52.845Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Information dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}],"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_info_uniprotkb.csv","filename":"bovine_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_info_uniprotkb.stat.csv","filename":"bovine_protein_info_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":341,"last_update":"2024-11-11T15:58:52.845207Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001232/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001232/DRAFT","spec_version":"1.3.0","etag":"a7c7feee180846de87eb1331fb1c45af6785b8a408af62c539325f3c8018566a","provenance_domain":{"name":"Bovine Proteome Masterlist (UniProtKB)","version":"v-x.x.x","created":"2024-11-11T16:10:32","modified":"2024-11-11T16:11:35.058Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Proteome Masterlist dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}],"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_masterlist.csv","filename":"bovine_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_masterlist.stat.csv","filename":"bovine_protein_masterlist.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":354,"last_update":"2024-11-11T16:11:35.058868Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001233/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001233/DRAFT","spec_version":"1.3.0","etag":"46f8371e088ae5a6ccdd8f04be38129229b75a3e5dfb8e9a0905e7b98cdeafb6","provenance_domain":{"name":"Bovine Reactions Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-11-11T15:48:00.000Z","modified":"2024-11-11T20:51:57.978Z","contributors":[{"name":"Jeet Vora","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Reactions (Rhea) dataset contains reactions information for pathways for Bos taurus [taxid:9913] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen\""],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","input_list":[]}],"keywords":["Rhea","Reactions","Participants","Enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_reactions_rhea.csv","filename":"bovine_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_reactions_rhea.stat.csv","filename":"bovine_protein_reactions_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":402,"last_update":"2024-11-11T20:51:57.978028Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001234/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001234/DRAFT","spec_version":"1.3.0","etag":"adf443f3c08bd4d2b10667cfc5b60af669b18c455cca10ee4bd35cf3a03f5bec","provenance_domain":{"name":"Bovine UniProtKB Xref Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T16:32:54.736Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref Rhea contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset.","input_list":[]}],"keywords":["reactions","Rhea","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_rhea.csv","filename":"bovine_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_rhea.stat.csv","filename":"bovine_protein_xref_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":297,"last_update":"2024-11-11T16:32:54.736795Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001235/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001235/DRAFT","spec_version":"1.3.0","etag":"9782383d965f6774300f4f2043aa0b1f8d40e92b22a73c5c48613c29e396e0dc","provenance_domain":{"name":"Bovine UniProtKB Xref Reactome","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-11-11T16:40:23","modified":"2024-11-11T16:47:21.575Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref Reactome contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}],"keywords":["pathways","reactions","REACTOME","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_reactome.csv","filename":"bovine_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_reactome.stat.csv","filename":"bovine_protein_xref_reactome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":419,"last_update":"2024-11-11T16:47:21.575549Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001236/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001236/DRAFT","spec_version":"1.3.0","etag":"ca4eaa7e041cc07744ab0c3eb66d6b8b338c92afafe88c487860a9f641e7476f","provenance_domain":{"name":"Bovine Protein Signal Peptide","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T17:27:31.838Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Signal Peptide dataset contains Bos taurus [taxid:9913] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}],"keywords":["signal peptide","ptm processing","UniProtKB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_annotation.csv","filename":"bovine_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_peptidesequences.fasta","filename":"bovine_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_cleavedsequences.fasta","filename":"bovine_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_fullsequences.fasta","filename":"bovine_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_annotation.stat.csv","filename":"bovine_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_peptidesequences.stat.csv","filename":"bovine_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_cleavedsequences.stat.csv","filename":"bovine_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_signalp_fullsequences.stat.csv","filename":"bovine_protein_signalp_fullsequences.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":822,"last_update":"2024-11-11T17:27:31.838132Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001237/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001237/DRAFT","spec_version":"1.3.0","etag":"70a66ef672a08e8dc3ec62a5adcd017ea863ab282641883137169b8eeaa7d4c6","provenance_domain":{"name":"Bovine UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T17:47:28.945Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref InterPro contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}],"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_interpro.csv","filename":"bovine_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_interpro.stat.csv","filename":"bovine_protein_xref_interpro.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":559,"last_update":"2024-11-11T17:47:28.945693Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001238/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001238/DRAFT","spec_version":"1.3.0","etag":"52aea6790177ee1a1ae1a94e6e6583121d5d63f7d056c3ac02103cb8bd1ef1b3","provenance_domain":{"name":"Bovine Glycosyltransferases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T17:55:02.006Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"jeetvora@gwu.edu"},{"name":"Hayley Dingerdissen","affiliation":"The George Washington University","contribution":["authoredBy"],"email":"hmhamilt@gwmail.gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycosyltransferases dataset contains list of Bos taurus [taxid:9913] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the pig proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Sus scrofa (Pig) [9823]\". To retrieve the list of all pig glycosyltransferases, the full list of pig proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}],"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_glycosyltransferase.csv","filename":"bovine_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_glycosyltransferase.stat.csv","filename":"bovine_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":2382,"last_update":"2024-11-11T17:55:02.006664Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001239/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001239/DRAFT","spec_version":"1.3.0","etag":"c4e442beacd82eb634eed361453b61bfd8dd6e593a6365b3210ae5e4a22e8bf3","provenance_domain":{"name":"Bovine UniProtKB Xref CDD","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T18:43:35.010Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref CDD contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["protein domains","CDD","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_cdd.csv","filename":"bovine_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_cdd.stat.csv","filename":"bovine_protein_xref_cdd.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":509,"last_update":"2024-11-11T18:43:35.010570Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001240/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001240/DRAFT","spec_version":"1.3.0","etag":"f6fa306a060b266ffd01d1bb35e4352a0479049ae709c7295cd55bbdd86092e1","provenance_domain":{"name":"Bovine UniProtKB Xref Bgee","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-11-11T18:51:27","modified":"2024-11-11T18:53:37.154Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","email":"k.warner1@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Bovine UniProtKB Xref Bgee dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["gene expression","Bgee","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_bgee.csv","filename":"bovine_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_bgee.stat.csv","filename":"bovine_protein_xref_bgee.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":567,"last_update":"2024-11-11T18:53:37.154756Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001241/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001241/DRAFT","spec_version":"1.3.0","etag":"c7138ec23e2e934aff0f78932098c920ccba5712a9c5ac19fbd842910e012018","provenance_domain":{"name":"Bovine Protein Recommended Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T19:00:40.366Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","email":"sbhuiyan28@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for Bos taurus [taxid:9913] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}],"keywords":["protein recommended name","protein name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_recnames.csv","filename":"bovine_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_recnames.stat.csv","filename":"bovine_protein_recnames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":272,"last_update":"2024-11-11T19:00:40.366175Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001242/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001242/DRAFT","spec_version":"1.3.0","etag":"4de6d3867d66a79ea531e7fdeb5827e808bbeb84a23912ab3d2562522db479f6","provenance_domain":{"name":"Bovine UniProtKB Xref OrthoDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T19:08:24.137Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref OrthoDB contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}],"keywords":["orthologs","OrthoDB","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_orthodb.csv","filename":"bovine_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_orthodb.stat.csv","filename":"bovine_protein_xref_orthodb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":512,"last_update":"2024-11-11T19:08:24.137025Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001243/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001243/DRAFT","spec_version":"1.3.0","etag":"43e0c130e712f8b1cea3a96bc55f0c0527427f34dca531d8032b946a45421062","provenance_domain":{"name":"Bovine UniProtKB Xref ChEMBL","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T19:26:09.267Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniprotKB Xref ChEMBL contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["bioactivity","ChEMBL","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_chembl.csv","filename":"bovine_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_chembl.stat.csv","filename":"bovine_protein_xref_chembl.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ChEMBL cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":433,"last_update":"2024-11-11T19:26:09.267170Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001244/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001244/DRAFT","spec_version":"1.3.0","etag":"9bb3389cd445a90d651c73ef8bb152454aa4f9b54803f3bc8946da766513a969","provenance_domain":{"name":"Bovine Protein Citations (RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T19:36:10.445Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Citations (RefSeq) datasets contains Bos taurus [taxid:9913] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions."}],"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_refseq.csv","filename":"bovine_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_refseq.stat.csv","filename":"bovine_protein_citations_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":378,"last_update":"2024-11-11T19:36:10.445464Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001245/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001245/DRAFT","spec_version":"1.3.0","etag":"21edf6ba10838c7de2f01225b35542ed8f129209fba147ce6ca6c6e19e33f09b","provenance_domain":{"name":"Bovine Protein Submitted Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T19:44:24.223Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","email":"luke.johnson@email.gwu.edu","contribution":["createdBy"]},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Bos taurus [taxid:9913] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}],"keywords":["protein submitted name","protein name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_submittednames.csv","filename":"bovine_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_submittednames.stat.csv","filename":"bovine_protein_submittednames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2024-11-11T19:44:24.223432Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001246/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001246/DRAFT","spec_version":"1.3.0","etag":"a25187d50b311b45adef96675cfa14005cba5428f292de466de1a39b535175e1","provenance_domain":{"name":"Bovine Protein Function (NCBI Refseq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T19:50:56.731Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Protein Function (NCBI RefSeq) dataset contains biological function annotation of Bos taurus [taxid:9913] genes from GeneRIF section in the NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions"}],"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_function_refseq.csv","filename":"bovine_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_function_refseq.stat.csv","filename":"bovine_protein_function_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2024-11-11T19:50:56.731324Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001247/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001247/DRAFT","spec_version":"1.3.0","etag":"69b9d6c70ea5170660cf0f98e47f2d1cc9cc10e2f781cf43d744a400dea62283","provenance_domain":{"name":"Arabidopsis EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-11-11T20:00:33","modified":"2024-11-11T20:02:12.211Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jingyue.wu@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis EBI-UniProtKB NT file contains proteome data for Arabidopsis thaliana [taxid:3702] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"input_list":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}],"keywords":["NT","proteome","EMBL-EBI"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_ntdata.nt","filename":"arabidopsis_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_ntdata.stat.csv","filename":"arabidopsis_protein_ntdata.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":345,"last_update":"2024-11-11T20:02:12.211716Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001248/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001248/DRAFT","spec_version":"1.3.0","etag":"db4fe9b0daf08bdc320b83a7de586483986e4d264fcead35f256e58a092e52b8","provenance_domain":{"name":"Arabidopsis UniProtKB Xref Araport","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T20:28:07.435Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniprotKB Xref Arabidopsis Information Portal (Araport) contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to Araport database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Araport was a database of Arabidopsis gene sequences and associated annotations that has been discontinued. Teams from The Arabidopsis Information Resource (TAIR), the National Center for Genome Resources (NCGR), and the Bio-Analytic Resource for Plant Biology (BAR) have taken over its operation and have refreshed/expanded the functionalities that were available at Araport."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Araport database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["Araport","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_araport.csv","filename":"arabidopsis_protein_xref_araport.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_araport.stat.csv","filename":"arabidopsis_protein_xref_araport.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Araport cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":813,"last_update":"2024-11-11T20:28:07.435008Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001249/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001249/DRAFT","spec_version":"1.3.0","etag":"8e4b5dba98c18dc0fabf94558b631477d9d47c2335d469dac482a643a0e18b0f","provenance_domain":{"name":"Arabidopsis UniProtKB Xref TAIR","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2024-11-11T20:40:39.023Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniprotKB Xref Arabidopsis Information Resource (TAIR) contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to TAIR database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","TAIR is a database of genetic and molecular biology data for Arabidopsis thaliana. Information includes gene structure, gene function, gene expression, DNA and seed stocks, genome maps, genetic and physical markers, publications, and information about the Arabidopsis research community."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to TAIR database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}],"keywords":["TAIR","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_tair.csv","filename":"arabidopsis_protein_xref_tair.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_tair.stat.csv","filename":"arabidopsis_protein_xref_tair.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"TAIR cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":702,"last_update":"2024-11-11T20:40:39.023891Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001250/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001250/DRAFT","etag":"39e0361e290e2c76cca7640ed70667e7ae8cd838e08e00274f5e25539f7f8a86","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish O-GlcNAc Glycosylation Sites (MCW)","version":"v-x-x-x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:48:29.540934","modified":"2024-12-10T17:36:36.458Z","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Stephanie Olivier-Van Stichelen","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"solivier@mcw.edu"},{"name":"Eugenia Wulff-Fuentes","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ewulff@mcw.edu"},{"name":" Rex R. Berendt","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"rberendt@mcw.edu"},{"name":" Logan Massman","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"lmassman@mcw.edu"},{"name":"Laura Danner","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"email":"ldanner@mcw.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish O-GlcNAc Glycosylation Sites (MCW) contains Danio rerio[taxid:7955] O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Zebrafish O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s zebrafish protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to zebrafish species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding zebrafish UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["O-GlcNAc"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":2985,"last_update":"2025-01-22T18:25:00.938996Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001251/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001251/DRAFT","spec_version":"1.3.0","etag":"6b06f64ad9f3881f9de98289af705c6edbfb916d908184d558afb60173f73162","provenance_domain":{"name":"Mouse Glycosylation Sites (GlyCosmos)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2022-08-16T20:48:29.540934","modified":"2025-08-03T22:24:30.214Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The GlyCosmos Mouse Glycosylation Sites dataset contains information on Asn (N)-glycosylated proteins and their glycosylation sites in *Mus musculus* [taxid:10090]. This dataset originates from GlycoProtDB (https://acgg.asia/db/gpdb/) and is made available to GlyGen through GlyCosmos (https://glycosmos.org/). The identification of glycoproteins in mouse models was carried out using LC/MS techniques as part of the Structural Glycomics Project, supported by NEDO (New Energy and Industrial Technology Development Organization) and the RIO Database Project by AIST. The development of the database was further supported by MEXT’s Integrated Database Project and the Program for Coordination Toward Integration of Related Databases, led by the Japan Science and Technology Agency (JST)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.","input_list":[]}],"keywords":["Glycosylation Sites","GlyCosmos","GlycoProtDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_glycosmos.csv","filename":"mouse_proteoform_glycosylation_sites_glycosmos.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_glycosmos.stat.csv","filename":"mouse_proteoform_glycosylation_sites_glycosmos.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites (GlyCosmos)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":948,"last_update":"2025-08-03T22:24:30.214912Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001252/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001252/DRAFT","spec_version":"1.3.0","etag":"84233543db363abcd24b70c6e48429e52433b07588c7f46a361ca03f78271832","provenance_domain":{"name":"Zebrafish Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:57:18.780Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Danio rerio [TaxID: 7955], based on a study using CRISPR/Cas9 to knock down GnT-Ib activity and assess the effects of reduced complex N-glycans on survival, development, and sensory-motor functions [PMID: 37998752]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_tablemaker.csv","filename":"zebrafish_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Danio rerio"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":549,"last_update":"2025-05-29T15:57:18.780346Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001253/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001253/DRAFT","spec_version":"1.3.0","etag":"3526f9f1379ab2a28b59fef731185645e80f6911c4ae9d1352979edc73936b87","provenance_domain":{"name":"Fruitfly Glycan Tissue Expression TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:55:27.632Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruit Fly Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Drosophila melanogaster [TaxID: 7227], based on a study examining glycan expression changes due to altered Tollo/Toll-8 signaling by analyzing the complete N-linked glycan profile of wild-type and mutant embryos [PMID: 17264077]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details can be found here: https://glygen.ccrc.uga.edu/tablemaker/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_tablemaker.csv","filename":"fruitfly_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":588,"last_update":"2025-05-29T15:55:27.632136Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001254/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001254/DRAFT","spec_version":"1.3.0","etag":"162e04585bd5a625bbb77abfa0a800bed084f0769cc5d41bbee0450f01fd346b","provenance_domain":{"name":"Human C-mannosylation Glycosylation Sites","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-01-24T18:28:33","modified":"2025-03-13T12:12:13.835Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human C-Man Glycosylation Sites contains Homo sapiens [taxid:9606] experimentally verified C-mannosylation sites from UniProtKB, that GlyGen has added the standard C-mannosylation saccharide alpha D-mannopyranose (G61491DK). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script checks that the UniProtKB ACs are the UniProtKB canonical sequences."}],"keywords":["C-mannosylation","C-Man"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_c_man.csv","filename":"human_proteoform_glycosylation_sites_c_man.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"C-mannosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2025-03-13T12:12:13.835114Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001255/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001255/DRAFT","spec_version":"1.3.0","etag":"567ba062e9378e929e6ec68741237d11050c851328e16449bc9f4a78de17b612","provenance_domain":{"name":"Mouse C-mannosylation Glycosylation Sites","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-01-24T18:45:06","modified":"2025-03-13T12:16:43.416Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy","curatedBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse C-Man Glycosylation Sites contains Mus musculus [taxid:10090] experimentally verified C-mannosylation sites from UniProtKB, that GlyGen has added the standard C-mannosylation saccharide alpha D-mannopyranose (G61491DK). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script checks the UniProtKB ACs are the UniProtKB canonical sequences."}],"keywords":["C-mannosylation","C-Man"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_c_man.csv","filename":"mouse_proteoform_glycosylation_sites_c_man.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"C-mannosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2025-03-13T12:16:43.416554Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001256/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001256/DRAFT","spec_version":"1.3.0","etag":"9562da32a96bf84ad677c79be10b5d10660da7775cce4923f1573686a01f814a","provenance_domain":{"name":"Bovine C-mannosylation Glycosylation Sites","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-03-13T12:12:50","modified":"2025-03-13T12:15:19.580Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine C-Man Glycosylation Sites contains Bos taurus [taxid:9913] experimentally verified C-mannosylation sites from UniProtKB, that GlyGen has added the standard C-mannosylation saccharide alpha D-mannopyranose (G61491DK). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script checks the UniProtKB ACs are the UniProtKB canonical sequences"}],"keywords":["C-mannosylation","C-Man"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_c_man.csv","filename":"bovine_proteoform_glycosylation_sites_c_man.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"C-mannosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":387,"last_update":"2025-03-13T12:15:19.580288Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001257/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001257/DRAFT","etag":"1bc6e6d552990b7ea13c69f1b4ddf4f39c48aa5cc711ad1188ba04a91d8164ca","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly UniProtKB Xref AGR","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly UniProtKB Xref AGR dataset contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions cross-referenced to AGR database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, AGR, and GlyGen","The AGR (Alliance of Genome Resources) is a consortium of seven model organism databases (MODs) and the Gene Ontology (GO) Consortium, whose goal is to provide an integrated view of their data to all biologists, clinicians and other interested parties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AGR cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","homologs","AGR","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AGR database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_alliance_genome_resources.csv","filename":"fruitfly_protein_xref_alliance_genome_resources.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_alliance_genome_resources.stat.csv","filename":"fruitfly_protein_xref_alliance_genome_resources.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":631,"last_update":"2025-03-11T17:30:29.324983Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001258/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001258/DRAFT","etag":"7a867daeeb0f9d2b160ef044a0d1ab975bc97e9411cce07235ddef6b80905f42","spec_version":"1.3.0","provenance_domain":{"name":"Human UniProtKB Xref AGR","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniProtKB Xref AGR dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to AGR database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, AGR, and GlyGen","The AGR (Alliance of Genome Resources) is a consortium of seven model organism databases (MODs) and the Gene Ontology (GO) Consortium, whose goal is to provide an integrated view of their data to all biologists, clinicians and other interested parties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AGR cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","homologs","AGR","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AGR database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_alliance_genome_resources.csv","filename":"human_protein_xref_alliance_genome_resources.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_alliance_genome_resources.stat.csv","filename":"human_protein_xref_alliance_genome_resources.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":614,"last_update":"2025-03-11T17:31:42.535988Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001259/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001259/DRAFT","etag":"9ace793dbbb193c41509df2909953f269fc55ca3b112b0033486f15ff109688c","spec_version":"1.3.0","provenance_domain":{"name":"Mouse UniProtKB Xref AGR","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse UniProtKB Xref AGR dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to AGR database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, AGR, and GlyGen","The AGR (Alliance of Genome Resources) is a consortium of seven model organism databases (MODs) and the Gene Ontology (GO) Consortium, whose goal is to provide an integrated view of their data to all biologists, clinicians and other interested parties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AGR cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","homologs","AGR","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AGR database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_alliance_genome_resources.csv","filename":"mouse_protein_xref_alliance_genome_resources.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_alliance_genome_resources.stat.csv","filename":"mouse_protein_xref_alliance_genome_resources.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":615,"last_update":"2025-03-11T17:32:50.438854Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001260/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001260/DRAFT","etag":"c2105f38797fcccdbe09cb113fa2416d6ed5436857f04b20b0f48653ce054b97","spec_version":"1.3.0","provenance_domain":{"name":"Rat UniProtKB Xref AGR","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat UniProtKB Xref AGR dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to AGR database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, AGR, and GlyGen","The AGR (Alliance of Genome Resources) is a consortium of seven model organism databases (MODs) and the Gene Ontology (GO) Consortium, whose goal is to provide an integrated view of their data to all biologists, clinicians and other interested parties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AGR cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","homologs","AGR","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AGR database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_alliance_genome_resources.csv","filename":"rat_protein_xref_alliance_genome_resources.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_alliance_genome_resources.stat.csv","filename":"rat_protein_xref_alliance_genome_resources.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":619,"last_update":"2025-03-11T17:33:54.275464Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001261/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001261/DRAFT","etag":"f681a9f728f28de5d4c835130be0025d2ed00ab7a5064517bacc9267f8fb9654","spec_version":"1.3.0","provenance_domain":{"name":"Yeast UniProtKB Xref AGR","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref AGR dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to AGR database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, AGR, and GlyGen","The AGR (Alliance of Genome Resources) is a consortium of seven model organism databases (MODs) and the Gene Ontology (GO) Consortium, whose goal is to provide an integrated view of their data to all biologists, clinicians and other interested parties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AGR cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","homologs","AGR","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AGR database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_alliance_genome_resources.csv","filename":"yeast_protein_xref_alliance_genome_resources.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_alliance_genome_resources.stat.csv","filename":"yeast_protein_xref_alliance_genome_resources.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":638,"last_update":"2025-03-11T17:34:43.116216Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001262/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001262/DRAFT","etag":"8f1695fa5e2941b081275ff44d4bd5b5c7b661d4113209566e15aa52642743a3","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref AGR","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref AGR dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to AGR database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, AGR, and GlyGen","The AGR (Alliance of Genome Resources) is a consortium of seven model organism databases (MODs) and the Gene Ontology (GO) Consortium, whose goal is to provide an integrated view of their data to all biologists, clinicians and other interested parties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AGR cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","homologs","AGR","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AGR database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_alliance_genome_resources.csv","filename":"zebrafish_protein_xref_alliance_genome_resources.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_alliance_genome_resources.stat.csv","filename":"zebrafish_protein_xref_alliance_genome_resources.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":618,"last_update":"2025-03-11T17:37:07.965998Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001263/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001263/DRAFT","etag":"ee54d01573cea601d7c421eb2212de934e4a5f7fe224e1a37614ef4df6b57a72","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Isoform sequences (UniProtKB) dataset contains Danio rerio [taxid:7955] protein fasta sequences for the zebrafish isoform accessions from the UniProtKB database,. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all zebrafish isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_allsequences.fasta","filename":"zebrafish_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_allsequences.stat.csv","filename":"zebrafish_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":335,"last_update":"2025-03-11T17:39:51.646134Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001264/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001264/DRAFT","etag":"2c388f73d28ed2aa0070a4f675390388419c2d0d177408cd5ad3ce63e6f8b289","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Danio rerio [taxid:7955] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_altnames.csv","filename":"zebrafish_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_altnames.stat.csv","filename":"zebrafish_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":275,"last_update":"2025-03-11T17:40:47.761176Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001265/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001265/DRAFT","etag":"3a0923e13c01783a643f70cde1cef4df1350e55aed88fc461926797b07e5cd47","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref AlphaFold contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","prerequisite":[],"output_list":[]}],"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_alphafolddb.csv","filename":"zebrafish_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_alphafolddb.stat.csv","filename":"zebrafish_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":456,"last_update":"2025-03-11T17:41:37.448094Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001266/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001266/DRAFT","etag":"c6eabebd4489457734dce4c950ec8be78c52ada165ff71745ff789b92b313ded","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Binary Interactions (IntAct)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Binary Interaction (IntAct) dataset contains Danio rerio [taxid:7955] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":0,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_binary_interactions.csv","filename":"zebrafish_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_binary_interactions.stat.csv","filename":"zebrafish_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":475,"last_update":"2025-03-11T17:50:23.415864Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001267/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001267/DRAFT","etag":"77bf2c256c8dfd63ae6f0266a3d5fc26bbd5ac708b6eb8d1b3d8c6658ea2e8f1","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Canonical (UniProtKB) Sequences dataset contains Danio rerio [taxid:7955] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all zebrafish canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_canonicalsequences.fasta","filename":"zebrafish_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_canonicalsequences.stat.csv","filename":"zebrafish_protein_canonicalsequences.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":305,"last_update":"2025-03-11T17:54:39.362166Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001268/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001268/DRAFT","etag":"b09db91c9d45c6b8a43c3f3da48c308d5f0c42649adf3db8516bc034effe98ee","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Citations dataset contains publication information for Danio rerio [taxid:7955] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_uniprotkb.csv","filename":"zebrafish_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_uniprotkb.stat.csv","filename":"zebrafish_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2025-03-11T17:56:41.154008Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001269/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001269/DRAFT","etag":"7d4994e86cc07a7cc72d7ef9c3bd91ad1e73eb78cd91e0ebc8d03deb6fa07739","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Citations (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2025-03-19T15:59:48.111Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Reactions (Reactome) dataset contains reactions information for pathways for Danio rerio [taxid:7955] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_reactome.csv","filename":"zebrafish_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_reactome.stat.csv","filename":"zebrafish_protein_citations_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":401,"last_update":"2025-03-19T15:59:48.111525Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001270/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001270/DRAFT","etag":"af6162906bdbb260709e454b0453e7689ddb840d839fca3206aab07128e2337d","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Citations (RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","affiliation":"","contribution":["contributedBy"],"email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Citations (RefSeq) datasets contains Danio rerio [taxid:7955] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_refseq.csv","filename":"zebrafish_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_refseq.stat.csv","filename":"zebrafish_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":384,"last_update":"2025-03-11T17:59:42.556212Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001271/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001271/DRAFT","etag":"3bd5ca2d907b7a1d285e2f7be2c08510d192bd49340f7078b44e79fc80a09770","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Function (NCBI Refseq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Function (NCBI RefSeq) dataset contains biological function annotation of Danio rerio [taxid:7955] genes from GeneRIF section in the NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_function_refseq.csv","filename":"zebrafish_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_function_refseq.stat.csv","filename":"zebrafish_protein_function_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":319,"last_update":"2025-03-11T18:01:00.739642Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001272/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001272/DRAFT","etag":"fc2bd5a639fba3ebc300494e0e0a50eba50511ff8c9dbadc7e39dcb8fc9b2f18","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Enzyme Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Enzyme Annotation (UniProtKB) dataset contains Danio rerio [taxid:7955] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_enzyme_annotation_uniprotkb.csv","filename":"zebrafish_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"zebrafish_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2025-03-12T10:28:34.597397Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001273/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001273/DRAFT","etag":"36381c47743afd9d295144db077982c0d8f9ddbbb8df765fcc573ab7463882be","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Function (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Function (UniProtKB) dataset contains biological function annotation for Danio rerio [taxid:7955] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_function_uniprotkb.csv","filename":"zebrafish_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_function_uniprotkb.stat.csv","filename":"zebrafish_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":317,"last_update":"2025-03-12T10:29:27.838047Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001274/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001274/DRAFT","spec_version":"1.3.0","etag":"cb7714d1cf53ef9805082bcdd222c2a98877cf2e70657865a478d66c3f37092a","provenance_domain":{"name":"Zebrafish Gene Symbols (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Zebrafish Gene Symbols (NCBI RefSeq) dataset contains Danio rerio [taxid:7955] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","prerequisite":[],"output_list":[]}],"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_genenames_refseq.csv","filename":"zebrafish_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_genenames_refseq.stat.csv","filename":"zebrafish_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":306,"last_update":"2025-03-12T10:33:24.875997Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001275/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001275/DRAFT","etag":"f50b094bb7b4305275a444321d1179e4093b43d5498f3a716ac4c9db83062ce8","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Danio rerio [taxid:7955] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_genenames_uniprotkb.csv","filename":"zebrafish_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_genenames_uniprotkb.stat.csv","filename":"zebrafish_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":492,"last_update":"2025-03-12T10:35:21.713624Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001276/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001276/DRAFT","spec_version":"1.3.0","etag":"cffd82686ef787f003187205ff8d11b4181a8bfb5d09b561f5444ca34829eb83","provenance_domain":{"name":"Zebrafish Glycosyltransferases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycosyltransferases dataset contains list of Danio rerio [taxid:7955] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the zebrafish proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Danio rerio (Zebrafish) [7955]\". To retrieve the list of all zebrafish glycosyltransferases, the full list of zebrafish proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list. For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession","prerequisite":[],"output_list":[]}],"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_glycosyltransferase.csv","filename":"zebrafish_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_glycosyltransferase.stat.csv","filename":"zebrafish_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":2415,"last_update":"2025-03-12T10:50:18.276779Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001277/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001277/DRAFT","spec_version":"1.3.0","etag":"5ad621d4a96dead5653df5dc5401fd5955ba310356a19834b9924184d82b4751","provenance_domain":{"name":"Zebrafish Glycohydrolases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycohydrolases dataset contains a list of Danio rerio [taxid:7955] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession","prerequisite":[],"output_list":[]}],"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_glycohydrolase.csv","filename":"zebrafish_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_glycohydrolase.stat.csv","filename":"zebrafish_protein_glycohydrolase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2025-03-12T10:51:10.858070Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001278/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001278/DRAFT","etag":"e8b6f136c0afef8203f4bf644bfc33400699769d1afd36288d348eacb5d21e27","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish N-Glycosylation Sequon","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Danio rerio [taxid:7955] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_glycosylation_motifs.csv","filename":"zebrafish_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_glycosylation_motifs.stat.csv","filename":"zebrafish_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":413,"last_update":"2025-03-12T10:53:07.756672Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001279/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001279/DRAFT","etag":"16e4c626fb1f7e86e35385f8ef7a54b43ae137bf066fb8a2c1095010bfaa7544","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Gene Ontology (GO) dataset contains Danio rerio [taxid:7955] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_go_annotation.csv","filename":"zebrafish_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_go_annotation.stat.csv","filename":"zebrafish_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":323,"last_update":"2025-03-12T10:56:39.185271Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001280/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001280/DRAFT","etag":"036f194ac2ef988f85c294e65ed4ba3b79ac895c82ce7eb1924d1d4852a5ff38","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Information (NCBI RefSeq) dataset contains Danio rerio [taxid:7955] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_info_refseq.csv","filename":"zebrafish_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_info_refseq.stat.csv","filename":"zebrafish_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":353,"last_update":"2025-03-12T10:58:26.489939Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001281/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001281/DRAFT","etag":"1216685b5c2ba5da013da25633029dc169663a1a0704d8731596d33033e38756","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Information dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_info_uniprotkb.csv","filename":"zebrafish_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_info_uniprotkb.stat.csv","filename":"zebrafish_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":344,"last_update":"2025-03-12T11:00:07.220571Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001282/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001282/DRAFT","etag":"05038e1a3cd1dbacd964f65f753abcfb5d0133235df3c17b1acbd16db5b709c3","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Proteome Masterlist (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Proteome Masterlist dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_masterlist.csv","filename":"zebrafish_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_masterlist.stat.csv","filename":"zebrafish_protein_masterlist.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":359,"last_update":"2025-03-12T11:02:33.128844Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001283/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001283/DRAFT","etag":"5b59ca176e46ae3a03be4a47f37b14edb1f6e762a1503018c57619c60932bd90","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish NCBI Protein Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish NCBI Protein Linkouts contains Danio rerio [taxid:7955] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_ncbi_linkouts.csv","filename":"zebrafish_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_ncbi_linkouts.stat.csv","filename":"zebrafish_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":311,"last_update":"2025-03-12T11:04:27.355515Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001284/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001284/DRAFT","etag":"22ae3a85918d08c0e53c7ac49d956898362cf459e58b710c9d01af76429d7b5c","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish EBI-UniProtKB NT file contains proteome data for Danio rerio [taxid:7955] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","version":"","step_number":0,"input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_ntdata.nt","filename":"zebrafish_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_ntdata.stat.csv","filename":"zebrafish_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":332,"last_update":"2025-03-12T11:05:57.661172Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001285/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001285/DRAFT","etag":"a2f5267d92b4477ac4aad4b900f0f15a7c2ce109cac60a302294c41ada843a11","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Reaction Participants (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Danio rerio [taxid:7955] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[],"prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_participants_reactome.csv","filename":"zebrafish_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_participants_reactome.stat.csv","filename":"zebrafish_protein_participants_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":455,"last_update":"2025-03-12T11:12:44.898630Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001286/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001286/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"151a5ef29b0871d91e20104606a6299c282ec1f90d886e15a919935e1ae38615","provenance_domain":{"name":"Zebrafish Reaction Participants (Rhea)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for Danio rerio [taxid:7955] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","version":"","prerequisite":[],"input_list":[],"output_list":[]}],"keywords":["Rhea","Participants","Reactions"]},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_participants_rhea.csv","filename":"zebrafish_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_participants_rhea.stat.csv","filename":"zebrafish_protein_participants_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":439,"last_update":"2025-03-12T11:29:43.610436Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001287/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001287/DRAFT","etag":"75f42a503375adf1dc94528d4b665674b3142529fbe5df488f857330c3fc89fc","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Pathways (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Pathways (Reactome) dataset contains Danio rerio [taxid:7955] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen.","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome Pathway","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome Pathways for UniProtKB canonical accessions from the triplestore containing triples from nt file and extracts the data as a csv dataset","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_pathways_reactome.csv","filename":"zebrafish_protein_pathways_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_pathways_reactome.stat.csv","filename":"zebrafish_protein_pathways_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":441,"last_update":"2025-03-12T11:31:02.767520Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001288/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001288/DRAFT","etag":"d1cfa67cf162caec86af2bf4bc651a5e73490478db0ffc131c940972ac030c06","spec_version":"1.3.0","provenance_domain":{"name":"Protein Resource Ontology [Zebrafish]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Darren Natale","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"dan5@georgetown.edu"},{"name":"Matthew Campbell ","affiliation":"UniCarbKB","contribution":["contributedBy"],"email":"m.campbell2@griffith.edu.au"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for Danio rerio [taxid:7955] proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale) and a python script was used to convert the source file into a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_pro_annotation.csv","filename":"zebrafish_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_pro_annotation.stat.csv","filename":"zebrafish_protein_pro_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":241,"last_update":"2025-03-12T12:11:17.241759Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001289/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001289/DRAFT","spec_version":"1.3.0","etag":"c60bf3968de6cdbde5d30de2ad6916909ad902bdcf214d70942fc0eca2f3def5","provenance_domain":{"name":"Zebrafish O-GlcNAc Glycosylation Sites (MCW)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-13T14:01:04.287Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish O-GlcNAc Glycosylation Sites (MCW) contains Danio rerio [taxid:7955] O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also contains disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ","Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Fruitfly O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s zebrafish protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to zebrafish species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding zebrafish UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein’s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field."}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.csv","filename":"zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":2983,"last_update":"2025-03-13T14:01:04.287695Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001290/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001290/DRAFT","spec_version":"1.3.0","etag":"d2ddbde910025ac6e43715fd75040fb184274faf223ae9da33a3bd1b4a770b63","provenance_domain":{"name":"Zebrafish Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycosylation Sites (UniProtKB) dataset contains Danio rerio [TaxID:7955] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Danio rerio proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_uniprotkb.csv","filename":"zebrafish_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":336,"last_update":"2025-03-12T15:48:51.552971Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001291/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001291/DRAFT","etag":"c2cfafedb8ab4b7c71a5d84b03dce28573bf4a6d10a3617c0b02488831e0b2c0","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Phosphorylation Sites (iPTMNet)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Phosphorylation Sites (iPTMNet) dataset contains Danio rerio [TaxID:7955] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_phosphorylation_sites_iptmnet.csv","filename":"zebrafish_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"zebrafish_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2025-03-12T15:52:33.835061Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001292/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001292/DRAFT","etag":"2247aca949ddb589fde1973b410661d0be30aa76d264ac43235fb13c3c450864","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Phosphorylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Phosphorylation Sites (UniProtKB) dataset contains Danio rerio [TaxID:7955] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"zebrafish_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"zebrafish_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":379,"last_update":"2025-03-12T15:53:50.782267Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001293/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001293/DRAFT","spec_version":"1.3.0","etag":"13da540bb6c76aac9dff209f5dc5c11ebb4002adf5035e6b63f9ab4793f01c77","provenance_domain":{"name":"Zebrafish Proteoform Phosphorylation Citations (iPTMnet)","version":"v-x.x.x","created":"","modified":"","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Proteoform Citations (iPTMNet) contains Danio rerio [TaxID:7955] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"zebrafish_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"zebrafish_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2025-03-12T15:56:16.362351Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001294/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001294/DRAFT","spec_version":"1.3.0","etag":"6ec57d300968e37c3b87a17f0685cef32fed884559fae4d0e7d16f743bc04374","provenance_domain":{"name":"Zebrafish Proteoform Phosphorylation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-09T14:51:20.183Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Proteoform Phosphorylation Citations (UniProtKB) dataset contains Danio rerio [TaxID:7955] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"zebrafish_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"zebrafish_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":348,"last_update":"2025-10-09T14:51:20.183072Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001295/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001295/DRAFT","spec_version":"1.3.0","etag":"cf9bde3b2e5e74e22d0330faaf4ebf0f04e6eca829b8ccd3c20a9ad157480317","provenance_domain":{"name":"Zebrafish Proteoform Glycosylation Citations (UniProtKB)","version":"v-x.x.x","created":"","modified":"","contributors":[{"contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Proteoform Glycosylation Citations (UniProtKB) dataset contains Danio rerio [TaxID:7955] citation details of the publications present in the dataset Zebrafish Glycosylation Sites (UniProtKB) (https://data.glygen.org/GLY_000038)."],"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_uniprotkb.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"parametric_domain":[{"value":""}],"error_domain":{},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":295,"last_update":"2025-03-12T15:58:37.475249Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001296/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001296/DRAFT","spec_version":"1.3.0","etag":"2d276e841fec186114ca5642f718ba4bb331bb00ab1c22258480632ba74b0859","provenance_domain":{"name":"Zebrafish O-GlcNAc Glycosylation Citations (MCW)","version":"v-x.x.x","created":"","modified":"","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Zebrafish O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Zebrafish O-GlcNAc Glycosylation Sites (MCW)  https://data.glygen.org/GLY_000517 for Danio rerio [TaxID: 7955] , contributed by Stephanie Olivier's group."],"description_domain":{"keywords":["O-GlcNAc","Publications","Citations","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. "}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":333,"last_update":"2025-03-12T16:00:38.177046Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001297/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001297/DRAFT","spec_version":"1.3.0","etag":"83e9bddc4b380cad9dda16880bc79d8c659adbe12bb07908ef87bfaed1606581","provenance_domain":{"name":"Hamster Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycosylation Sites (UniProtKB) dataset contains Cricetulus griseus [TaxID:10029] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Cricetulus griseus proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hamster_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hamster_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2025-03-12T16:02:44.085286Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001298/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001298/DRAFT","etag":"8fe08bbabc1948c09f2ea53d69a5a761357bd41781cf9b387d8d2d5cb3ae84ea","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Phosphorylation Sites (iPTMNet)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Phosphorylation Sites (iPTMNet) dataset contains Cricetulus griseus [TaxID:10029] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_phosphorylation_sites_iptmnet.csv","filename":"hamster_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"hamster_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":367,"last_update":"2025-03-12T16:04:49.192832Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001299/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001299/DRAFT","spec_version":"1.3.0","etag":"101258e94bc99abce104c17ed41c87d4d3af9091a833bb359046308b4df707de","provenance_domain":{"name":"Hamster Proteoform Phosphorylation Citations (iPTMnet)","version":"v-x.x.x","created":"","modified":"","contributors":[{"email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Proteoform Citations (iPTMNet) contains Cricetulus griseus [TaxID:10029] publication information of phosphorylated proteins from iPTMnet. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from iPTMnet. If you use this dataset please provide proper attribution to iPTMnet and GlyGen."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_phosphorylation_sites_iptmnet.csv","filename":"hamster_proteoform_citations_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv","filename":"hamster_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations (iPTMnet)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":428,"last_update":"2025-03-12T16:06:14.922553Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001300/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001300/DRAFT","etag":"28e17d69cd09452944f413ea9dd944c1e0da7f39f6d234975c76063135b73cf2","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Phosphorylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Phosphorylation Sites (UniProtKB) dataset contains Cricetulus griseus [TaxID:10029] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hamster_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hamster_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":386,"last_update":"2025-03-12T16:07:27.345878Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001301/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001301/DRAFT","spec_version":"1.3.0","etag":"75001e97a65e60ff270c2952d44fe205befe191bb5eab3174f519593a062ef3b","provenance_domain":{"name":"Hamster Proteoform Phosphorylation Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-09T14:53:42.732Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Proteoform Phosphorylation Citations (UniProtKB) dataset contains Cricetulus griseus [TaxID:10029] publication information of glycoproteins from UniProtKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed","Phosphorylation"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_phosphorylation_sites_uniprotkb.csv","filename":"hamster_proteoform_citations_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv","filename":"hamster_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Citations UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":355,"last_update":"2025-10-09T14:53:42.732425Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001302/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001302/DRAFT","spec_version":"1.3.0","etag":"87f9c19ef5fd66eb62d9901204218fa6a9d5a469c743b2b7c1f8883279d3b8d1","provenance_domain":{"name":"Hamster Proteoform Citations (GlyConnect)","version":"v-x.x.x","created":"","modified":"","embargo":{"start_time":"","end_time":""},"contributors":[{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"license":"https://creativecommons.org/licenses/by/4.0/"},"usability_domain":["The Hamster Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329 for Cricetulus griseus [TaxID:10029]. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"platform":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_glycosylation_sites_glyconnect.csv","filename":"hamster_proteoform_citations_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_glycosylation_sites_glyconnect.stat.csv","filename":"hamster_proteoform_citations_glycosylation_sites_glyconnect.stat.csv"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}]},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":579,"last_update":"2025-03-12T16:13:37.312685Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001303/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001303/DRAFT","etag":"1740eea4fd9769ea22d8f0888447d201746eb35221bd4187d9be3af6cb51da11","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Glycosylation Sites (GlyConnect) ","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Frederique Lisacek","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"frederique.lisacek@sib.swiss"},{"name":"Julien Mariethoz","affiliation":"GlyConnect","contribution":["contributedBy"],"email":"julien.mariethoz@sib.swiss"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycosylation Sites (GlyConnect) dataset contains Cricetulus griseus [TaxID:10029] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Cricetulus griseus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (hamster_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_glyconnect.csv","filename":"hamster_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"hamster_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":648,"last_update":"2025-03-12T16:14:41.115155Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001304/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001304/DRAFT","spec_version":"1.3.0","etag":"a868331268f54f245465b57b8e9d0ca901c9f00e210c92e6a4db645e39dbf51b","provenance_domain":{"name":"Zebrafish Glycosylation Sites (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.909814","modified":"2026-03-23T16:09:33.746Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jasmine Young","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"jasmine@rcsb.rutgers.edu"},{"name":"Chenghua Shao","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"chenghua@rcsb.rutgers.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycosylation Sites (RCSB PDB) dataset contains Danio rerio [taxid:7955] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"input_list":[]}],"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_pdb.csv","filename":"zebrafish_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_pdb.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":511,"last_update":"2026-03-23T16:09:33.746822Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001305/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001305/DRAFT","etag":"2d2a282786f424fa4ca0e8e1d5bddb16ac76739826498e6c4e848ac7853b8a9a","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Names (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Names (NCBI RefSeq) dataset contains Danio rerio [taxid:7955] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_proteinnames_refseq.csv","filename":"zebrafish_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_proteinnames_refseq.stat.csv","filename":"zebrafish_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":320,"last_update":"2025-03-12T16:32:07.800502Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001306/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001306/DRAFT","spec_version":"1.3.0","etag":"14d565f2afc48e6fb49a311af493984da7bfa01e9b27796a83fde87f90309dd5","provenance_domain":{"name":"Hamster Glycosylation Sites (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-01-23T17:21:05.909814","modified":"2026-08-19T10:02:35.623Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Jasmine Young","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"jasmine@rcsb.rutgers.edu"},{"name":"Chenghua Shao","affiliation":"RCSB PDB","contribution":["contributedBy"],"email":"chenghua@rcsb.rutgers.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycosylation Sites (RCSB PDB) dataset contains Cricetulus griseus [taxid:10029] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"input_list":[]}],"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_pdb.csv","filename":"hamster_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_pdb.stat.csv","filename":"hamster_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":518,"last_update":"2026-08-19T10:02:35.623225Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001307/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001307/DRAFT","etag":"316edacbc31cf8a819bd42c72f44b656ebc849c0f8da62772e5e8c55de8fe742","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein PTM Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein PTM Annotation (UniProtKB) dataset contains Danio rerio [taxid:7955] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_ptm_annotation_uniprotkb.csv","filename":"zebrafish_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_ptm_annotation_uniprotkb.stat.csv","filename":"zebrafish_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":381,"last_update":"2025-03-12T16:34:11.773748Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001308/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001308/DRAFT","etag":"7aa122e00f5ba7d76677ba5759810e848db6e3a9cc6955c9dbc608662c0ad13a","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Reactions (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Reactions (Reactome) dataset contains reactions information for pathways for Danio rerio [taxid:7955] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_reactions_reactome.csv","filename":"zebrafish_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_reactions_reactome.stat.csv","filename":"zebrafish_protein_reactions_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":402,"last_update":"2025-03-12T16:35:14.720319Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001309/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001309/DRAFT","etag":"c2aa500051ce9d26882506569bfda279fe70378384a76b1aa5c6c5f9c133dc2b","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Reactions Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"","affiliation":"","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Reactions (Rhea) dataset contains reactions information for pathways for Danio rerio [taxid:7955] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Reactions","Participants","Enzymes"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"description":"The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_reactions_rhea.csv","filename":"zebrafish_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_reactions_rhea.stat.csv","filename":"zebrafish_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":407,"last_update":"2025-03-12T16:39:16.893130Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001310/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001310/DRAFT","etag":"b5efcc0691853f7a8b83bce662abc54ffdbb0129a2926b16cf93bbfed1c8cb02","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Recommended Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Recommended Names (UniProtKB) dataset contains Danio rerio [taxid:7955] UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_recnames.csv","filename":"zebrafish_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_recnames.stat.csv","filename":"zebrafish_protein_recnames.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":276,"last_update":"2025-03-12T16:40:39.716571Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001311/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001311/DRAFT","etag":"28c9c0cbbbfd555fa9c36a9ce8626617cf8ed01e0ed2fb54c057a1087d909251","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Sequence Info (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Sequence Info (UniProtKB) dataset contains Danio rerio [taxid:7955] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all zebrafish isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_sequenceinfo.csv","filename":"zebrafish_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_sequenceinfo.stat.csv","filename":"zebrafish_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":335,"last_update":"2025-03-12T16:42:00.352362Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001312/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001312/DRAFT","etag":"2bd1fc281aac72f812d8b5d4cad3a6ca98723ea81b0b1ca8191459f045778b55","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Signal Peptide","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Signal Peptide dataset contains Danio rerio [taxid:7955] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_annotation.csv","filename":"zebrafish_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_peptidesequences.fasta","filename":"zebrafish_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_cleavedsequences.fasta","filename":"zebrafish_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_fullsequences.fasta","filename":"zebrafish_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_annotation.stat.csv","filename":"zebrafish_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_peptidesequences.stat.csv","filename":"zebrafish_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_cleavedsequences.stat.csv","filename":"zebrafish_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_signalp_fullsequences.stat.csv","filename":"zebrafish_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":827,"last_update":"2025-03-12T16:43:32.355866Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001313/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001313/DRAFT","etag":"75cb2f5a9a06fde7e111a9dcbda2562b9c634bba1ddbe36317a9927f6db00207","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Site Annotation","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Site Annotation (UniProtKB) dataset contains Danio rerio [taxid:7955] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_site_annotation_uniprotkb.csv","filename":"zebrafish_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_site_annotation_uniprotkb.stat.csv","filename":"zebrafish_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":381,"last_update":"2025-03-12T16:55:32.391688Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001314/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001314/DRAFT","etag":"81233b3ef0a63bdbc23f714e237a13a4db03957b66400b8088f954927c9a4af4","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Protein Submitted Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Danio rerio [taxid:7955] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_submittednames.csv","filename":"zebrafish_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_submittednames.stat.csv","filename":"zebrafish_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":618,"last_update":"2025-03-12T16:56:29.664399Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001315/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001315/DRAFT","etag":"6c723164897760ab7a22451d5ec1e44b0318567ec66ba1bd384d6978de2ccc3f","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref Bgee","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref Bgee dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_bgee.csv","filename":"zebrafish_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_bgee.stat.csv","filename":"zebrafish_protein_xref_bgee.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":572,"last_update":"2025-03-12T17:10:02.523490Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001316/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001316/DRAFT","etag":"7192a4d363caca07c2266ea7551a60757889bf41be607f7e500aad862c639a15","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref BRENDA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniprotKB Xref BRENDA contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_brenda.csv","filename":"zebrafish_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_brenda.stat.csv","filename":"zebrafish_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":579,"last_update":"2025-03-12T17:11:20.434493Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001317/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001317/DRAFT","etag":"ea5e7ba5adbb1269a33505130f3f6adfcb4e7479d64f032c0aba3a851742be16","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref CAZy","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniprotKB Xref CAZy contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_cazy.csv","filename":"zebrafish_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_cazy.stat.csv","filename":"zebrafish_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":566,"last_update":"2025-03-12T17:12:20.367741Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001318/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001318/DRAFT","etag":"e3c2b755c47af22042d8f231553a795f2cbb0285f68e3251195a5f2a229a66e1","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref CDD","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref CDD contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_cdd.csv","filename":"zebrafish_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_cdd.stat.csv","filename":"zebrafish_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":512,"last_update":"2025-03-12T17:13:16.368592Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001319/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001319/DRAFT","etag":"8f6779b475724e7578e4d97d62c7ac32460cce3738b6e668ed49412bf94091cb","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref ChEMBL","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniprotKB Xref ChEMBL contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_chembl.csv","filename":"zebrafish_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_chembl.stat.csv","filename":"zebrafish_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":435,"last_update":"2025-03-12T17:14:39.052180Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001320/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001320/DRAFT","etag":"a3c10421390f7d1a659550ba1627cd765f2580ea01855654b28c89481e713391","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref NCBI Gene","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref NCBI Gene dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_geneid.csv","filename":"zebrafish_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_geneid.stat.csv","filename":"zebrafish_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2025-03-12T17:15:37.243551Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001321/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001321/DRAFT","etag":"753ccfce4747bae55a714e37ad049e02a227a211e93e52e81bc18f6ea4d82be2","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref IntAct","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref IntAct dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_intact.csv","filename":"zebrafish_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_intact.stat.csv","filename":"zebrafish_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":643,"last_update":"2025-03-12T17:42:29.157928Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001322/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001322/DRAFT","etag":"e34b646c2ab64439dd85bb2497b0540b5bbba1592bdb536c4262a7b6c360ff2c","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref InterPro contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_interpro.csv","filename":"zebrafish_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_interpro.stat.csv","filename":"zebrafish_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":564,"last_update":"2025-03-12T17:43:39.321439Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001323/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001323/DRAFT","etag":"f92f52dab98df222aaafc4f34838be8d25618f780d1e8314baaacba13ecf1405","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref KEGG PATHWAY","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref KEGG PATHWAY contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_kegg.csv","filename":"zebrafish_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_kegg.stat.csv","filename":"zebrafish_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":498,"last_update":"2025-03-12T17:56:12.533821Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001324/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001324/DRAFT","etag":"f726b4808134918bc0926875cac3766161f383e6b3b837718d65bf9399a2a7c6","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_uniprotkb.csv","filename":"hamster_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_uniprotkb.stat.csv","filename":"hamster_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":320,"last_update":"2025-03-12T18:10:07.105935Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001325/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001325/DRAFT","etag":"e6906ca5b93605a8d89e11d1091e6e71bd843b4ea297bfb7b281a8ab3fc37c91","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"","affiliation":"","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","affiliation":"","contribution":["contributedBy"],"email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref Rhea contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_rhea.csv","filename":"hamster_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_rhea.stat.csv","filename":"hamster_protein_xref_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":311,"last_update":"2025-03-12T18:11:24.538274Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001326/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001326/DRAFT","etag":"411549374b175aa7fa6791dde7914b62312f1af746afa9ad3d5faa62ece9e8d0","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniprotKB Xref RefSeq contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_refseq.csv","filename":"hamster_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_refseq.stat.csv","filename":"hamster_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":776,"last_update":"2025-03-12T18:12:36.611914Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001327/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001327/DRAFT","etag":"cb8f51a6f20160c9215961b160a8f4502fd1b54b1d72555b88b92aef78da58d3","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref PRO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniprotKB Xref PRO contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pro.csv","filename":"hamster_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pro.stat.csv","filename":"hamster_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":480,"last_update":"2025-03-12T18:14:43.144871Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001328/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001328/DRAFT","etag":"2b9ed542380dec88938b83bf210b5af0154fa2054d0e26cc5799bb4293b08cf5","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref Pfam","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref Pfam contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pfam.csv","filename":"hamster_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pfam.stat.csv","filename":"hamster_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":481,"last_update":"2025-03-12T18:16:34.137127Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001329/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001329/DRAFT","etag":"a0a56eb0783db4a7b2e6138e6ad18f15773986dd0681bf838ff3efd7840dffa0","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref PANTHER","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref PANTHER contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_panther.csv","filename":"hamster_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_panther.stat.csv","filename":"hamster_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":571,"last_update":"2025-03-12T18:18:21.819466Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001330/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001330/DRAFT","etag":"332e8dcff8450b6ed341f5f831eee2058e297f909822dd1bdae03b4f6902bcf1","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref OrthoDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref OrthoDB contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_orthodb.csv","filename":"hamster_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_orthodb.stat.csv","filename":"hamster_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":524,"last_update":"2025-03-12T18:21:40.096050Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001331/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001331/DRAFT","etag":"18c67ffdaa730dc9590266186bc97d9b791c8193f30d8a7392616b04fd126262","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref OMA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref OMA contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_oma.csv","filename":"hamster_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_oma.stat.csv","filename":"hamster_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":445,"last_update":"2025-03-12T18:23:11.163858Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001332/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001332/DRAFT","etag":"78fbb7f44d02547cd67bb565d8584d30855413f3c183fd4caf346c09c2706151","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref KEGG PATHWAY","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref KEGG PATHWAY contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_kegg.csv","filename":"hamster_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_kegg.stat.csv","filename":"hamster_protein_xref_kegg.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":505,"last_update":"2025-03-12T18:24:40.076114Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001333/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001333/DRAFT","etag":"2d454d390efcac92a5cbbb48077cb4a014bd735c410ff19b9934b0bc732ee631","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref InterPro contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_interpro.csv","filename":"hamster_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_interpro.stat.csv","filename":"hamster_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":571,"last_update":"2025-03-12T18:25:55.148302Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001334/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001334/DRAFT","etag":"2bab70fd8c9e7d189e07872035434ea568ecc1b2021499c02486c4db36823fd1","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref IntAct","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref IntAct dataset contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_intact.csv","filename":"hamster_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_intact.stat.csv","filename":"hamster_protein_xref_intact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":650,"last_update":"2025-03-12T18:27:28.665658Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001335/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001335/DRAFT","spec_version":"1.3.0","etag":"bd3d7ab0c7be2e3fa6efa328efffd678b0ed5f0518fd27be05dd6804f70bd11c","provenance_domain":{"name":"Hamster UniProtKB xref GlyConnect","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-03-23T20:06:54.916Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Hamster UniProtKB xref GlyConnect dataset contains Cricetulus griseus (taxid:10029) UniProtKB canonical accessions mapped to the GlyConnect IDs."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the Glyconnect Database IDs"}],"keywords":["Xref","GlyConnect"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_glyconnect.csv","filename":"hamster_protein_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_glyconnect.stat.csv","filename":"hamster_protein_xref_glyconnect.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyConnect Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":177,"last_update":"2026-03-23T20:06:54.916429Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001336/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001336/DRAFT","etag":"781d29062f13b273fc57dc25a9333406b2f65a0345ca70b3c43d225879ee7c53","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref NCBI Gene","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref NCBI Gene dataset contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_geneid.csv","filename":"hamster_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_geneid.stat.csv","filename":"hamster_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":620,"last_update":"2025-03-12T18:30:04.781316Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001337/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001337/DRAFT","etag":"8c1e9213615c18b85f776149d9cc2d4ffaf41d804c189ed00b3d5af7f5bd4f93","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref ChEMBL","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniprotKB Xref ChEMBL contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_chembl.csv","filename":"hamster_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_chembl.stat.csv","filename":"hamster_protein_xref_chembl.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":444,"last_update":"2025-03-12T18:31:17.780999Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001338/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001338/DRAFT","etag":"62115c9c37edb880d5063741df9984af794314b4243b88aa96e063d585d80729","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref CDD","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref CDD contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_cdd.csv","filename":"hamster_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_cdd.stat.csv","filename":"hamster_protein_xref_cdd.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":519,"last_update":"2025-03-12T18:32:34.517716Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001339/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001339/DRAFT","etag":"af21386f93564ed1cc30099058a9b77a69a913fc91103e708fd4ffb853de7c0d","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref CAZy","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniprotKB Xref CAZy contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_cazy.csv","filename":"hamster_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_cazy.stat.csv","filename":"hamster_protein_xref_cazy.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":573,"last_update":"2025-03-12T19:09:17.168688Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001340/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001340/DRAFT","etag":"bdc111ed370007aa81d2c5048d976fcb0e3cd01dc7d1b3b69fb4168c143ed4fe","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref BRENDA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniprotKB Xref BRENDA contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_brenda.csv","filename":"hamster_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_brenda.stat.csv","filename":"hamster_protein_xref_brenda.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":587,"last_update":"2025-03-12T19:10:18.927047Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001341/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001341/DRAFT","etag":"e5b89e7036c0fd455994438a9c55cfd4309ca45b8ee313eecb386512df2a5e98","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Submitted Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Cricetulus griseus [taxid:10029] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_submittednames.csv","filename":"hamster_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_submittednames.stat.csv","filename":"hamster_protein_submittednames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":625,"last_update":"2025-03-12T19:11:10.748593Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001342/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001342/DRAFT","etag":"6a16375e28642bd7292cc4baf064b5a228b7fff4c5d073d58b8ccd4009649432","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Site Annotation","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Site Annotation (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_site_annotation_uniprotkb.csv","filename":"hamster_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_site_annotation_uniprotkb.stat.csv","filename":"hamster_protein_site_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2025-03-12T19:13:37.595575Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001343/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001343/DRAFT","etag":"0d04bbcc39718f8e3697609e634540f9135f9f151df469c55d19760609b75a60","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Signal Peptide","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Signal Peptide dataset contains Cricetulus griseus [taxid:10029] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_annotation.csv","filename":"hamster_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_peptidesequences.fasta","filename":"hamster_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_cleavedsequences.fasta","filename":"hamster_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_fullsequences.fasta","filename":"hamster_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_annotation.stat.csv","filename":"hamster_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_peptidesequences.stat.csv","filename":"hamster_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_cleavedsequences.stat.csv","filename":"hamster_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_signalp_fullsequences.stat.csv","filename":"hamster_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":835,"last_update":"2025-03-12T19:17:15.116369Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001344/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001344/DRAFT","etag":"449426f2c8f5cbde338c70f7aabc05bdcb7e7ce69a07f68f30290f854208a5bf","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Sequence Info (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Sequence Info (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all hamster isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_sequenceinfo.csv","filename":"hamster_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_sequenceinfo.stat.csv","filename":"hamster_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":342,"last_update":"2025-03-12T19:20:08.608264Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001345/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001345/DRAFT","etag":"5201a2ac087060df8dceeff4beb17db3eb7283550e8c0f491a2c227d7ba9518e","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Recommended Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Recommended Names (UniProtKB) dataset contains Cricetulus griseus [taxid:10029]  UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_recnames.csv","filename":"hamster_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_recnames.stat.csv","filename":"hamster_protein_recnames.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":284,"last_update":"2025-03-12T19:21:23.812514Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001346/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001346/DRAFT","spec_version":"1.3.0","etag":"39fb7418c38e60ea9edb58a82bb76b5f689c1de65a341a87868a0c8b91c19109","provenance_domain":{"name":"Zebrafish Xref The O-GlcNAc Database","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Eugenia Wulff-Fuentes","email":"ewulff@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Rex R. Berendt","email":"rberendt@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":" Logan Massman","email":"lmassman@mcw.edu"},{"affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Laura Danner","email":"ldanner@mcw.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["Zebrafish Xref The O-GlcNAc Database contains Danio rerio (taxid:7955) UniProtKB canonical accessions mapped to the The O-GlcNAc Database accessions."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the The O-GlcNAc Database accessions.","prerequisite":[],"output_list":[]}],"keywords":["O-GlcNAc"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_oglcnac_mcw.csv","filename":"zebrafish_protein_xref_oglcnac_mcw.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_oglcnac_mcw.stat.csv","filename":"zebrafish_protein_xref_oglcnac_mcw.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"The O-GlcNAc Database","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":183,"last_update":"2025-03-12T19:54:54.578495Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001347/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001347/DRAFT","etag":"8639f16bab135a6c36889fa1af78e4483f96e21753abf9e6590694f0abf1d3ef","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref OMA","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref OMA contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_oma.csv","filename":"zebrafish_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_oma.stat.csv","filename":"zebrafish_protein_xref_oma.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":438,"last_update":"2025-03-12T19:56:04.588889Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001348/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001348/DRAFT","etag":"dad158e263e166e28168f87b9d1aea72bb37048b2f5f8a88ca8c1e13a6d438db","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref OrthoDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref OrthoDB contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_orthodb.csv","filename":"zebrafish_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_orthodb.stat.csv","filename":"zebrafish_protein_xref_orthodb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":516,"last_update":"2025-03-12T20:02:48.837553Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001349/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001349/DRAFT","etag":"baa2036405d4b4a8767b3168a78d419574d6968b0afd5f9f49a496e7e1be766f","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref PANTHER","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref PANTHER contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_panther.csv","filename":"zebrafish_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_panther.stat.csv","filename":"zebrafish_protein_xref_panther.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":564,"last_update":"2025-03-12T20:03:54.914368Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001350/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001350/DRAFT","etag":"77c29d69269148b45b4140caea4d496d07678697d96fd5d5130fec9b7bfb4279","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref PDB contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pdb.csv","filename":"zebrafish_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pdb.stat.csv","filename":"zebrafish_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":474,"last_update":"2025-03-12T20:05:47.560471Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001351/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001351/DRAFT","etag":"c469ada2d2f02b933eb740157520801a50b407ddaf20354a3877289b34de3960","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref Pfam","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref Pfam contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pfam.csv","filename":"zebrafish_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pfam.stat.csv","filename":"zebrafish_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":473,"last_update":"2025-03-12T20:09:48.321537Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001352/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001352/DRAFT","etag":"22cb39a1ee40789c56d4df87264ffb9537d1b8c8abb5894353103382203c31d1","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref PRO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniprotKB Xref PRO contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pro.csv","filename":"zebrafish_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pro.stat.csv","filename":"zebrafish_protein_xref_pro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":470,"last_update":"2025-03-12T20:11:14.136258Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001353/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001353/DRAFT","etag":"46a4795fcb6d570aa48f17a98d73d930b8f87e138eb6beb4a8b231a666b1b7e2","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref Reactome","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref Reactome contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_reactome.csv","filename":"zebrafish_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_reactome.stat.csv","filename":"zebrafish_protein_xref_reactome.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":422,"last_update":"2025-03-12T20:20:15.147639Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001354/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001354/DRAFT","etag":"fc1ad14166589030dc3375a7ebcf212c682cf5b63c3a55b16896ffef146f4372","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniprotKB Xref RefSeq contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_refseq.csv","filename":"zebrafish_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_refseq.stat.csv","filename":"zebrafish_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":768,"last_update":"2025-03-12T20:21:32.734648Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001355/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001355/DRAFT","etag":"5000be92e304062be92e3f8da0d30779d640431d2ec117b7a6abcd981957d5e3","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"","affiliation":"","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","affiliation":"","contribution":["contributedBy"],"email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref Rhea contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rhea cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["reactions","Rhea","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_rhea.csv","filename":"zebrafish_protein_xref_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_rhea.stat.csv","filename":"zebrafish_protein_xref_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":302,"last_update":"2025-03-12T20:22:51.587709Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001356/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001356/DRAFT","etag":"e472edf10d310bdc19e65488969ffa69f8be629f84afa99e08b23efc5405d901","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref (UniProtKB) dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_uniprotkb.csv","filename":"zebrafish_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_uniprotkb.stat.csv","filename":"zebrafish_protein_xref_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2025-03-12T20:23:47.999845Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001357/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001357/DRAFT","etag":"bb5a10904e4bca267526fb19aa32d2e6cb5a09aabfe846da5c0986f237369545","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish UniProtKB Xref ZFIN","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref ZFIN contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to ZFIN database accessions/identifiers. If you use this dataset please provide proper attribution to UniProtKB, ZFIN, and GlyGen","The Zebrafish Information Network (ZFIN) is a database of Zebrafish genetic and genomic data which provides a wide array of expertly curated, organized and cross-referenced zebrafish research data."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ZFIN cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Zebrafish Information Network","ZFIN","Zebrafish","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to flybase database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_zfin.csv","filename":"zebrafish_protein_xref_zfin.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_zfin.stat.csv","filename":"zebrafish_protein_xref_zfin.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":535,"last_update":"2025-03-12T20:37:05.854342Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001358/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001358/DRAFT","etag":"0230cc97e4af29a291af09cc9330d18b1e8f5ee5f62942287e3ca2a2c1a722b2","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Reactions Rhea","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"","affiliation":"","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Reactions (Rhea) dataset contains reactions information for pathways for Cricetulus griseus [taxid:10029] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Rhea","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Rhea","Reactions","Participants","Enzymes"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"description":"The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","prerequisite":[],"input_list":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_reactions_rhea.csv","filename":"hamster_protein_reactions_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_reactions_rhea.stat.csv","filename":"hamster_protein_reactions_rhea.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":414,"last_update":"2025-03-13T08:16:17.309814Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001359/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001359/DRAFT","etag":"bfc9ef69b1ad34f3ba83e0fec641542464416c383d3f869f37323c7b81368f13","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Reactions (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Reactions (Reactome) dataset contains reactions information for pathways for Cricetulus griseus [taxid:10029] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_reactions_reactome.csv","filename":"hamster_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_reactions_reactome.stat.csv","filename":"hamster_protein_reactions_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":409,"last_update":"2025-03-13T08:17:51.292620Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001360/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001360/DRAFT","etag":"6b52895917076cdc8f3496bd968d5370da691528317e918ee72d52d8f38f6ebf","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein PTM Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein PTM Annotation (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_ptm_annotation_uniprotkb.csv","filename":"hamster_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hamster_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2025-03-13T08:18:54.518320Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001361/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001361/DRAFT","etag":"b2b58519f943d88b2acdc0600d81d21b1a163a3be530a18f98605fe1207490e0","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Names (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Names (NCBI RefSeq) dataset contains Cricetulus griseus [taxid:10029] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_proteinnames_refseq.csv","filename":"hamster_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_proteinnames_refseq.stat.csv","filename":"hamster_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":327,"last_update":"2025-03-13T08:19:49.782946Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001362/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001362/DRAFT","etag":"96adf311f43d637c374d90f7e8475313415c26d4bbefefae2e1ca6c27a6c8967","spec_version":"1.3.0","provenance_domain":{"name":"Protein Resource Ontology [Hamster]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Darren Natale","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"dan5@georgetown.edu"},{"name":"Matthew Campbell ","affiliation":"UniCarbKB","contribution":["contributedBy"],"email":"m.campbell2@griffith.edu.au"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for Cricetulus griseus [taxid:10029] proteins."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"PRO ontology","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_pro_annotation.csv","filename":"hamster_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_pro_annotation.stat.csv","filename":"hamster_protein_pro_annotation.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":251,"last_update":"2025-03-13T08:21:06.591931Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001363/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001363/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"bb2da323a51828e65145cfbbc98521e20fbd8ce4ae9e4568ce55fac2f588ca3f","provenance_domain":{"name":"Hamster Reaction Participants (Rhea)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for Cricetulus griseus [taxid:10029] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen"],"description_domain":{"pipeline_steps":[{"step_number":1,"name":"make-protein-dataset.py","description":"The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","version":"","prerequisite":[],"input_list":[],"output_list":[]}],"keywords":["Rhea","Participants","Reactions"]},"parametric_domain":[{"param":"","value":"","step":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_participants_rhea.csv","filename":"hamster_protein_participants_rhea.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_participants_rhea.stat.csv","filename":"hamster_protein_participants_rhea.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"http://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Rhea)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":446,"last_update":"2025-03-13T08:22:07.993118Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001364/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001364/DRAFT","etag":"1d8ac2c6e49bcfcacb0c1efc82189d94f6a94aab6101dad5cc0f12bf378d2885","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Reaction Participants (Reactome)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for Cricetulus griseus [taxid:10029] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reaction Participants (Reactome)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Reactome","Participant"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"description":"The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.","input_list":[],"prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_participants_reactome.csv","filename":"hamster_protein_participants_reactome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_participants_reactome.stat.csv","filename":"hamster_protein_participants_reactome.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":462,"last_update":"2025-03-13T08:23:15.437250Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001365/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001365/DRAFT","etag":"e5fb5efb100b1acc3471634aaacef73383dd03edb2c09568c8675b5feede4180","spec_version":"1.3.0","provenance_domain":{"name":"Hamster EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster EBI-UniProtKB NT file contains proteome data for Cricetulus griseus [taxid:10029] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","version":"","step_number":0,"input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_ntdata.nt","filename":"hamster_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_ntdata.stat.csv","filename":"hamster_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":339,"last_update":"2025-03-13T08:24:22.332386Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001366/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001366/DRAFT","etag":"c8cae2d82b5137a7e1a70d9437381e0bf17c0021712fb80f96fdc0a6baee3b23","spec_version":"1.3.0","provenance_domain":{"name":"Hamster NCBI Protein Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster NCBI Protein Linkouts contains Cricetulus griseus [taxid:10029] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Gene Linkouts","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_ncbi_linkouts.csv","filename":"hamster_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_ncbi_linkouts.stat.csv","filename":"hamster_protein_ncbi_linkouts.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":318,"last_update":"2025-03-13T08:26:37.877507Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001367/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001367/DRAFT","etag":"d69e6993742ba40089c20516475cef6d2e28a590eb2c70c950511e1994768aac","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Proteome Masterlist (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Proteome Masterlist dataset contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_masterlist.csv","filename":"hamster_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_masterlist.stat.csv","filename":"hamster_protein_masterlist.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":366,"last_update":"2025-03-13T08:27:41.896316Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001368/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001368/DRAFT","etag":"fbb550c81374c30beb503cf5de71b8f10392ba3ba0b066d23e131e9453e8c1ce","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Information dataset contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_info_uniprotkb.csv","filename":"hamster_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_info_uniprotkb.stat.csv","filename":"hamster_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2025-03-13T08:28:42.556836Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001369/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001369/DRAFT","etag":"f963b758ffbd269c1b5ff98549f1f1d2c6407b56f6cd428e6a42656d37f0fbe8","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Information (NCBI RefSeq) dataset contains Cricetulus griseus [taxid:10029] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_info_refseq.csv","filename":"hamster_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_info_refseq.stat.csv","filename":"hamster_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2025-03-13T08:29:35.536330Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001370/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001370/DRAFT","etag":"f9e0f486ce277455b08e06d99f6690ae4c11a4d33a3e7a6e0a46ecaea2318737","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Gene Ontology (GO) dataset contains Cricetulus griseus [taxid:10029] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_go_annotation.csv","filename":"hamster_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_go_annotation.stat.csv","filename":"hamster_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":331,"last_update":"2025-03-13T08:30:38.678216Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001371/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001371/DRAFT","etag":"32ad6befb736ac8484ace7cda21e80bec0241f53535305ce1f4974fb1ff58b20","spec_version":"1.3.0","provenance_domain":{"name":"Hamster N-Glycosylation Sequon","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"2","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Cricetulus griseus [taxid:10029] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_glycosylation_motifs.csv","filename":"hamster_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_glycosylation_motifs.stat.csv","filename":"hamster_protein_glycosylation_motifs.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":420,"last_update":"2025-03-13T08:31:36.828323Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001372/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001372/DRAFT","spec_version":"1.3.0","etag":"c33195dc612b88e5e3123978861f8bb9b18331cf1700eb310027a38111893c07","provenance_domain":{"name":"Hamster Glycosyltransferases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycosyltransferases dataset contains list of Cricetulus griseus [taxid:10029] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the hamster proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Cricetulus griseus (Chinese hamster) [10029]\". To retrieve the list of all hamster glycosyltransferases, the full list of hamster proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession","prerequisite":[],"output_list":[]}],"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_glycosyltransferase.csv","filename":"hamster_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_glycosyltransferase.stat.csv","filename":"hamster_protein_glycosyltransferase.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":2433,"last_update":"2025-03-13T08:32:41.288967Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001373/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001373/DRAFT","etag":"d489d7110b013752fd73361a7ab1573a7ea768685cf4fb1391d96889e01d678d","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Cricetulus griseus [taxid:10029] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_genenames_uniprotkb.csv","filename":"hamster_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_genenames_uniprotkb.stat.csv","filename":"hamster_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":499,"last_update":"2025-03-13T08:33:42.212537Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001374/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001374/DRAFT","spec_version":"1.3.0","etag":"d2ce47afcd976d231c710b655cfebd9f1fc9db955643a554c3740df4bcc87693","provenance_domain":{"name":"Hamster Gene Symbols (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Jingyue Wu","affiliation":"The George Washington University","email":"jingyue.wu@email.gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Hamster Gene Symbols (NCBI RefSeq) dataset contains Cricetulus griseus [taxid:10029] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions","prerequisite":[],"output_list":[]}],"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_genenames_refseq.csv","filename":"hamster_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_genenames_refseq.stat.csv","filename":"hamster_protein_genenames_refseq.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2025-03-13T08:34:37.683217Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001375/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001375/DRAFT","etag":"e5742959b25084302da31a4a378df42c094099b272e63e6b33315bbb4138cbc8","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Isoform sequences (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] protein fasta sequences for the hamster isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hamster isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_allsequences.fasta","filename":"hamster_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_allsequences.stat.csv","filename":"hamster_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":339,"last_update":"2025-03-13T11:03:24.447754Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001376/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001376/DRAFT","etag":"fbfa95e7d8dddddb88985e013607c69845f2b3968f0a1dee53a2b5cd3316dd4f","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Cricetulus griseus [taxid:10029] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_altnames.csv","filename":"hamster_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_altnames.stat.csv","filename":"hamster_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":282,"last_update":"2025-03-13T11:04:51.944293Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001377/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001377/DRAFT","etag":"4cc450bcaaf9f5eb7426d82e67073464b3bd4e35912cd8672e0b046b59a7585d","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref AlphaFold","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref AlphaFold contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to AlphaFold database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The AlphaFold Protein Structure Database contains computationally predicted three-dimensional structures of proteins."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"AlphaFold cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to AlphaFold database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ","prerequisite":[],"output_list":[]}],"keywords":["protein 3D structure","AlphaFold","AlphaFolddb","cross-reference"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_alphafolddb.csv","filename":"hamster_protein_xref_alphafolddb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_alphafolddb.stat.csv","filename":"hamster_protein_xref_alphafolddb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":462,"last_update":"2025-03-13T11:07:15.208162Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001378/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001378/DRAFT","etag":"7128d49cc476df462e4cb1aca4cecfd635125d82af9a221f1377c6005d4e145a","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Binary Interactions (IntAct)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Binary Interaction (IntAct) dataset contains Cricetulus griseus [taxid:10029] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":0,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_binary_interactions.csv","filename":"hamster_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_binary_interactions.stat.csv","filename":"hamster_protein_binary_interactions.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":482,"last_update":"2025-03-13T11:09:36.244094Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001379/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001379/DRAFT","etag":"83729398fa994c2e4239f87df778f0d4b085da3e0aefd7ddeaffaa6a7473656f","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Canonical (UniProtKB) Sequences dataset contains Cricetulus griseus [taxid:10029] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all hamster canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_canonicalsequences.fasta","filename":"hamster_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_canonicalsequences.stat.csv","filename":"hamster_protein_canonicalsequences.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":312,"last_update":"2025-03-13T11:26:06.765666Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001380/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001380/DRAFT","etag":"20d0f64c1b5218b0ca514083c7b74cd20b294f6d60234266fdfd412ea4a5fbd9","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Citations dataset contains publication information for Cricetulus griseus [taxid:10029] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_uniprotkb.csv","filename":"hamster_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_uniprotkb.stat.csv","filename":"hamster_protein_citations_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":515,"last_update":"2025-03-13T11:27:45.942190Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001381/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001381/DRAFT","etag":"68d4266f5cc2db67e505e5acd85a6b52529b4e18e4491b04cb13a503c0d514c0","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Citations (RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Not Applicable","affiliation":"","contribution":["contributedBy"],"email":""},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Citations (RefSeq) datasets contains Cricetulus griseus [taxid:10029] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_refseq.csv","filename":"hamster_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_refseq.stat.csv","filename":"hamster_protein_citations_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":390,"last_update":"2025-03-13T11:29:31.814312Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001382/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001382/DRAFT","etag":"7bf04c086b97e7b1b83b8b509b600423431bdb82e4c91acb1ea2efc1e734ecd8","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Function (NCBI Refseq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Function (NCBI RefSeq) dataset contains biological function annotation of Cricetulus griseus [taxid:10029] genes from GeneRIF section in the NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accession to the UniProtKB Canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_function_refseq.csv","filename":"hamster_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_function_refseq.stat.csv","filename":"hamster_protein_function_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":325,"last_update":"2025-03-13T11:32:43.431860Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001383/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001383/DRAFT","etag":"7b1d8bbf2771270b7edd8c25dbbd893fdbd39593a273e3e1b6c5ca6d2a87e592","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Enzyme Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Enzyme Annotation (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_enzyme_annotation_uniprotkb.csv","filename":"hamster_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hamster_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":396,"last_update":"2025-03-13T11:35:13.904977Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001384/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001384/DRAFT","etag":"3924199a088dbb026d392382b25cedd2c625f22fc276131ac9d72503dfe78c3d","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Protein Function (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Protein Function (UniProtKB) dataset contains biological function annotation for Cricetulus griseus [taxid:10029] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_function_uniprotkb.csv","filename":"hamster_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_function_uniprotkb.stat.csv","filename":"hamster_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":323,"last_update":"2025-03-13T11:37:02.882141Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001385/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001385/DRAFT","etag":"6b8eec989b3eff21e0f7b3e3fb8f492e4f6d95e53019c0b7e02606f62b4d1a19","spec_version":"1.3.0","provenance_domain":{"name":"Human C-mannosylation Glycosylation Sites citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset contains publication information for the Human C-mannosylation Glycosylation Sites dataset: https://data.glygen.org/GLY_001254. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the canonical UniProt protein C-Man sites in the dataset to the origin publication.","prerequisite":[],"output_list":[]}],"keywords":["PMID","journal","citations","authors","Literature","PubMed","C-mannosylation","C-Man"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_c_man.csv","filename":"human_proteoform_citations_glycosylation_sites_c_man.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_c_man.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_c_man.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":283,"last_update":"2025-03-13T12:06:55.654106Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001386/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001386/DRAFT","spec_version":"1.3.0","etag":"f9942bd537bb833056f5dabcc2f12501ab3d2adf8e753df157cb0b8edc8a65be","provenance_domain":{"name":"Mouse C-mannosylation Glycosylation Sites citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-03-13T12:18:36.546Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset contains publication information for the Mouse C-mannosylation Glycosylation Sites dataset: https://data.glygen.org/GLY_001255. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the canonical UniProt protein C-Man sites in the dataset to the origin publication."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed","C-mannosylation","C-Man"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_glycosylation_sites_c_man.csv","filename":"mouse_proteoform_citations_glycosylation_sites_c_man.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_glycosylation_sites_c_man.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_c_man.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":283,"last_update":"2025-03-13T12:18:36.546702Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001387/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001387/DRAFT","etag":"2153206fd728fdb77c3e4088467501bf53a16dd989f22be4b8f785ddad2beec5","spec_version":"1.3.0","provenance_domain":{"name":"Bovine C-mannosylation Glycosylation Sites citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset contains publication information for the Bovine C-mannosylation Glycosylation Sites dataset: https://data.glygen.org/GLY_001256. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script maps the canonical UniProt protein C-Man sites in the dataset to the origin publication.","prerequisite":[],"output_list":[]}],"keywords":["PMID","journal","citations","authors","Literature","PubMed","C-mannosylation","C-Man"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_c_man.csv","filename":"bovine_proteoform_citations_glycosylation_sites_c_man.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_c_man.stat.csv","filename":"bovine_proteoform_citations_glycosylation_sites_c_man.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":284,"last_update":"2025-03-13T12:20:28.769388Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001388/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001388/DRAFT","etag":"b21571b1e839d8bc913ea5f3fcb047daa9be02301c062ee6c639fca03b9c8f9f","spec_version":"1.3.0","provenance_domain":{"name":"Hamster UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref PDB contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pdb.csv","filename":"hamster_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pdb.stat.csv","filename":"hamster_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":480,"last_update":"2025-03-13T12:24:37.680844Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001389/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001389/DRAFT","spec_version":"1.3.0","etag":"81551c417765056e0db60d78da3e4330940bf5aeb87773453839a006c9a44e20","provenance_domain":{"name":"Hamster GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster GlyGen-PDB Cross References dataset contains Cricetulus griseus [taxid:10029] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset.","prerequisite":[],"output_list":[]}],"keywords":["UniProtKB","GlyGen","PDB","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_pdb_map.csv","filename":"hamster_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_pdb_map.stat.csv","filename":"hamster_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":333,"last_update":"2025-03-17T15:27:53.715173Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001390/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001390/DRAFT","spec_version":"1.3.0","etag":"35e749b4c250d20ba5e8164c6e3e4b168d0ce7d83b52cc95a7f11481e5ba3b7a","provenance_domain":{"name":"Zebrafish GlyGen-PDB Cross References Mapping","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-03-21T10:43:09","modified":"2025-10-09T13:54:41.119Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish GlyGen-PDB Cross References dataset contains Danio rerio [taxid:7955] UniProtKB accessions mapped to PDB accessions for the purpose of PDB to GlyGen cross references. If you use this dataset please provide proper attribution to UniProtKB, PDB and GlyGen."],"description_domain":{"keywords":["UniProtKB","GlyGen","PDB","crossreferences"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions, maps them to PDB database accessions/identifiers, and extracts the data as a csv dataset"}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_pdb_map.csv","filename":"zebrafish_protein_pdb_map.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_pdb_map.stat.csv","filename":"zebrafish_protein_pdb_map.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PDB Cross References Mapping","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":326,"last_update":"2025-10-09T13:54:41.119891Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_001391/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001391/DRAFT","etag":"0b5ec3ff7f15c7f6ed62d80d2060dfc790ab2d549338bcd85de0edcbc07014eb","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:48:18","modified":"2024-12-05T16:16:44.558Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Predicted O-Glycosylation Sites dataset contains predicted Cricetulus griseus (TaxID: 10029) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes.","prerequisite":[],"output_list":[]},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset.","prerequisite":[],"output_list":[]}],"keywords":["O-Glycosylation","Predicted"]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}},{"uri":{"filename":"combine_csv.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"hamster_proteoform_glycosylation_sites_predicted_isoglyp.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv","filename":"hamster_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":769,"last_update":"2025-03-19T18:30:00.265536Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001392/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001392/DRAFT","etag":"ec797127ea3bdb34976eb371e54a08ac7ff2dcf1a12883c2666093669745be80","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:48:18","modified":"2024-12-05T16:16:44.558Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Predicted O-Glycosylation Sites dataset contains predicted Danio rerio (TaxID: 7955) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes.","prerequisite":[],"output_list":[]},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset.","prerequisite":[],"output_list":[]}],"keywords":["O-Glycosylation","Predicted"]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}},{"uri":{"filename":"combine_csv.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"zebrafish_proteoform_glycosylation_sites_predicted_isoglyp.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":762,"last_update":"2025-03-19T18:34:54.893567Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001393/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001393/DRAFT","spec_version":"1.3.0","etag":"987b417aee30f31c773b01d0feddb94f7bfb0012b3d6314d29ce9089b40570a2","provenance_domain":{"name":"Zebrafish Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Danio rerio [TaxID: 7955], based on a study using CRISPR/Cas9 to knock down GnT-Ib activity and assess the effects of reduced complex N-glycans on survival, development, and sensory-motor functions [PMID: 37998752]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/data/dataset/TD1127346."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Danio rerio"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":618,"last_update":"2025-03-19T18:51:57.365335Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001394/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001394/DRAFT","spec_version":"1.3.0","etag":"2ebb13941e50bff2175cb561b3f8517c731096d87a7a2eb0feb795ab040a30a6","provenance_domain":{"name":"Fruitfly Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Drosophila melanogaster [TaxID: 7227], based on a study using CRISPR/Cas9 to knock down GnT-Ib activity and assess the effects of reduced complex N-glycans on survival, development, and sensory-motor functions [PMID: 37998752]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/data/dataset/TD1127346."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":631,"last_update":"2025-03-19T18:55:35.310010Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001395/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001395/DRAFT","spec_version":"1.3.0","etag":"a8a72d2899f68863758dfec131c561b8a0c5e5a221d5bfd37fca6f3e559b2a6f","provenance_domain":{"name":"Glycan Xref BiomarkerKB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Nathan Edwards","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"nje5@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2025-03-19T20:08:24.110Z"},"usability_domain":["The dataset provides cross-references to BiomarkerKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source databases: https://glytoucan.org/;http://www.glycome-db.org/; https://biomarkerkb.org/"],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}],"keywords":["Glycan","GlyTouCan Accession","BiomarkerKB","Biomarkers","Cross-references","ID/Accession Mapping"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_biomarkerkb.csv","filename":"glycan_xref_biomarkerkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_biomarkerkb.stat.csv","filename":"glycan_xref_biomarkerkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BiomarkerKB cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":393,"last_update":"2025-03-19T20:08:24.110791Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001396/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001396/DRAFT","spec_version":"1.3.0","etag":"c118ba6e535d8c26b68ea4b0e85c3147cfd710c33100c464bc4433a19b6d7737","provenance_domain":{"name":"Human UniProtKB xref BiomarkerKB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}],"modified":"2025-03-19T20:32:39.913Z"},"usability_domain":["The Human UniProtKB Xref BiomarkerKB dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to BiomarkerKB database accessions/identifiers. If you use this dataset please provide proper attribution to UniProtKB, GlyGen and BiomarkerKB","The BiomarkerKB project is a Common Fund Data Ecosystem (CFDE) sponsored project to develop a knowledgebase that will organize and integrate biomarker data from different public sources."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script maps the UniProtKB accesions to the BiomarkerKB Database IDs"}],"keywords":["Xref","BiomarkerKB","Biomarkers"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_biomarkerkb.csv","filename":"human_protein_xref_biomarkerkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_biomarkerkb.stat.csv","filename":"human_protein_xref_biomarkerkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"BiomarkerKB Cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":552,"last_update":"2025-03-19T20:32:39.913035Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001397/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001397/DRAFT","spec_version":"1.3.0","etag":"b2269945cd722812358921b36a111aa4dccd7716a5b965f73124f8e0b75fcc54","provenance_domain":{"name":"Glycan Species Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:13:36.255Z","modified":"2025-04-11T18:08:01.662Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Glycan Species Citations dataset contains details of the publications for GlyGen Organisms."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}],"keywords":["Publications","Citations","PubMed","GlyTouCan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_citations_species.csv","filename":"glycan_citations_species.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_citations_species.stat.csv","filename":"glycan_citations_species.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan Species Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Arabidopsis thaliana"},{"category_name":"species","category_value":"Bos taurus"},{"category_name":"species","category_value":"Cricetulus griseus"},{"category_name":"species","category_value":"Danio rerio"},{"category_name":"species","category_value":"Gallus gallus"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H77)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":119,"last_update":"2025-04-11T18:08:01.662683Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001398/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001398/DRAFT","spec_version":"1.3.0","etag":"a2b48a601b6b15a02549a4210be1a3b89fa9d316e8cdffa4bacb3fe064219654","provenance_domain":{"name":"Pig Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T13:45:54","modified":"2025-04-15T14:09:38.916Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"George Washington University","contribution":["createdBy"],"email":"rykahsay@email.gwu.edu"},{"name":"Vijay Shanker","affiliation":"University of Delaware","contribution":["contributedBy"],"email":"vijay@udel.edu"},{"name":"Karen Ross","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"ker25@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Sus scrofa [taxid:9823] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tool 'GlycoSiteMiner' developed by the GlyGen team (https://github.com/glygener/glycositeminer). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000950)"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file."}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_literature_mining.csv","filename":"pig_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"pig_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":583,"last_update":"2025-04-15T14:09:38.916149Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001399/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001399/DRAFT","spec_version":"1.3.0","etag":"2c51fab232122d2245f96884bcf780c76f7946913271005a3e03e9249a843ce6","provenance_domain":{"name":"SARS-CoV2 Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T14:10:22","modified":"2025-04-15T14:12:00.629Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"George Washington University","contribution":["createdBy"],"email":"rykahsay@email.gwu.edu"},{"name":"Vijay Shanker","affiliation":"University of Delaware","contribution":["contributedBy"],"email":"vijay@udel.edu"},{"name":"Karen Ross","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"ker25@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tool 'GlycoSiteMiner' developed by the GlyGen team (https://github.com/glygener/glycositeminer). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000434)"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file."}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_literature_mining.csv","filename":"sarscov2_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":678,"last_update":"2025-04-15T14:12:00.629269Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001400/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001400/DRAFT","spec_version":"1.3.0","etag":"e252ea78993d8ce45307bd903f790ddf3cd9eed221df891ab14c4aa02ea35ab8","provenance_domain":{"name":"Fruitfly Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T13:38:47","modified":"2025-04-15T13:45:23.033Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"George Washington University","contribution":["createdBy"],"email":"rykahsay@email.gwu.edu"},{"name":"Vijay Shanker","affiliation":"University of Delaware","contribution":["contributedBy"],"email":"vijay@udel.edu"},{"name":"Karen Ross","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"ker25@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Drosophila melanogaster [taxid:7227] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tool 'GlycoSiteMiner' developed by the GlyGen team (https://github.com/glygener/glycositeminer). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000647)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file."}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_literature_mining.csv","filename":"fruitfly_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":606,"last_update":"2025-04-15T13:45:23.033604Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001401/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001401/DRAFT","spec_version":"1.3.0","etag":"36a008e1de2f6defa786d00eac6b062e7116c70c2be7bdb6847ac1ee9e5469f8","provenance_domain":{"name":"Chicken Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-04-15T12:56:29.076Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"George Washington University","contribution":["createdBy"],"email":"rykahsay@email.gwu.edu"},{"name":"Vijay Shanker","affiliation":"University of Delaware","contribution":["contributedBy"],"email":"vijay@udel.edu"},{"name":"Karen Ross","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"ker25@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Gallus gallus [taxid:9031] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tools 'RLIMS-G' developed by Dr. Vijay Shanker (University of Delaware) and 'GlycoSiteMiner' developed by the GlyGen team (https://github.com/glygener/glycositeminer). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000001)"],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file."}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_literature_mining.csv","filename":"chicken_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"chicken_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":677,"last_update":"2025-04-15T12:56:29.076477Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001402/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001402/DRAFT","spec_version":"1.3.0","etag":"f18a03bb210789559d441e0831c462861ee43682ecd7cee306f5a36e91ca6e45","provenance_domain":{"name":"Yeast Glycosylation Sites [Automatic Literature Mining] [Automatically verified]","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T14:13:11","modified":"2026-06-02T09:11:07.292Z","contributors":[{"name":"Jeet Vora","affiliation":"George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"George Washington University","contribution":["createdBy"],"email":"rykahsay@email.gwu.edu"},{"name":"Vijay Shanker","affiliation":"University of Delaware","contribution":["contributedBy"],"email":"vijay@udel.edu"},{"name":"Karen Ross","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"ker25@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset contains a list of Saccharomyces cerevisiae S288C [taxid:559292] proteins with information on glycosylation sites detected from PubMed database (abstracts-only) through the Automatic mining tool 'GlycoSiteMiner' developed by the GlyGen team (https://github.com/glygener/glycositeminer). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000760)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file."}],"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_literature_mining.csv","filename":"yeast_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"yeast_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2026-06-02T09:11:07.292282Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001403/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001403/DRAFT","spec_version":"1.3.0","etag":"cd6d16a5e1b94957e2cf9e1d1b07c54fbc9a3d30f6be4a38d0677509a28aa14d","provenance_domain":{"name":"Yeast Proteoform Citations (Literature Mining)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T14:32:39","modified":"2025-04-15T14:32:59.629Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Proteoform Citations [Automatic Literature Mining] dataset contains Saccharomyces cerevisiae S288C [taxid:559292] citation details of the publications present in the Yeast Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_001402)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"yeast_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"yeast_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":367,"last_update":"2025-04-15T14:32:59.629529Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001404/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001404/DRAFT","spec_version":"1.3.0","etag":"c2d054840444bfab3a9d2a0275ea0dc6e6ca1f9067b676893126fbfa7d857017","provenance_domain":{"name":"Pig Proteoform Citations (Literature Mining)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T14:33:17","modified":"2025-04-15T14:33:28.818Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Proteoform Citations [Automatic Literature Mining] dataset contains Sus scrofa [taxid:9823] citation details of the publications present in the Pig Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_001398)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"pig_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"pig_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":336,"last_update":"2025-04-15T14:33:28.818234Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001405/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001405/DRAFT","spec_version":"1.3.0","etag":"f1e30f37bde14ffd8f182e7f168c39e43b81733bb638736e50dd0ad7b92ce0f5","provenance_domain":{"name":"Chicken Proteoform Citations (Literature Mining)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T14:33:41","modified":"2025-04-15T14:34:04.373Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Proteoform Citations [Automatic Literature Mining] dataset contains Gallus gallus [taxid:9031] citation details of the publications present in the Chicken Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_001401)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"chicken_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"chicken_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":349,"last_update":"2025-04-15T14:34:04.373401Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001406/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001406/DRAFT","spec_version":"1.3.0","etag":"2972df030124e2eb1061839f8eaea9d4297c68597b721d3e15e9d2568d7635ad","provenance_domain":{"name":"Fruitfly Proteoform Citations (Literature Mining)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T14:34:36","modified":"2025-04-15T14:35:03.146Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Proteoform Citations [Automatic Literature Mining] dataset contains Drosophila melanogaster [taxid:7227] citation details of the publications present in the Fruitfly Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_001400)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"fruitfly_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2025-04-15T14:35:03.146730Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001407/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001407/DRAFT","spec_version":"1.3.0","etag":"4db48f9e74b770a30f3abb0c0111f9966adaf755adc842fad869286b326df024","provenance_domain":{"name":"SARS-CoV2 Proteoform Citations (Literature Mining)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-04-15T14:35:14","modified":"2025-04-15T14:35:25.411Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Proteoform Citations [Automatic Literature Mining] dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] citation details of the publications present in the SARS-CoV2 Glycosylation Sites [Automatic Literature Mining] [Automatically verified] dataset (https://data.glygen.org/GLY_001399)."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","Literature","PubMed"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_citations_glycosylation_sites_literature_mining.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_citations_glycosylation_sites_literature_mining.stat.csv","filename":"sarscov2_proteoform_citations_glycosylation_sites_literature_mining.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":438,"last_update":"2025-04-15T14:35:25.411040Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001408/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001408/DRAFT","spec_version":"1.3.0","etag":"00ac79648892ff61defb50c83a1e72e1e826601f2f49957682ad0a2d9d81fd54","provenance_domain":{"name":"Human Glycan Tissue Expression TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:55:26","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Homo sapiens [TaxID: 9606]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details can be found here: https://glygen.ccrc.uga.edu/tablemaker/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_tablemaker.csv","filename":"human_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"human_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":341,"last_update":"2025-05-29T16:05:29.975618Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001409/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001409/DRAFT","etag":"d7fd25f5cfb33570835231f394c05d6f42036c343c632188e71d0504e57e3005","spec_version":"1.3.0","provenance_domain":{"name":"Human Glycan GlycomeAtlas","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycan GlycomeAtlas dataset comprises human [TaxID: 9606] tissue glycan information for Homo sapiens. This data is provided by the GlycomeAtlas from GlyCosmos which provides comprehensive information on glycan structures catalogued from various publications. More information can be found here: https://glycosmos.org/glycomeatlas."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression GlycomeAtlas","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["GlycomeAtlas","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_glycomeatlas.csv","filename":"human_proteoform_glycosylation_sites_glycomeatlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_glycomeatlas.stat.csv","filename":"human_proteoform_glycosylation_sites_glycomeatlas.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":413,"last_update":"2025-06-03T17:09:56.392802Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001410/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001410/DRAFT","etag":"77eee15c9dfd58205ada613d39699a974ed570218334e7b9ef1334424babe016","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Glycan GlycomeAtlas","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycan GlycomeAtlas dataset comprises zebrafish [TaxID: 7955] tissue glycan information for Danio rerio. This data is provided by the GlycomeAtlas from GlyCosmos which provides comprehensive information on glycan structures catalogued from various publications. More information can be found here: https://glycosmos.org/glycomeatlas."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression GlycomeAtlas","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Danio rerio"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["GlycomeAtlas","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_glycomeatlas.csv","filename":"zebrafish_proteoform_glycosylation_sites_glycomeatlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_glycomeatlas.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_glycomeatlas.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2025-06-03T17:15:12.431505Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001411/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001411/DRAFT","etag":"9cdc824b667d2343183ea44604d0e9b4e0c5b86ea5a5ceef4ae368360548f249","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Glycan GlycomeAtlas","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycan GlycomeAtlas dataset comprises mouse [TaxID: 10090] tissue glycan information for Mus musculus. This data is provided by the GlycomeAtlas from GlyCosmos which provides comprehensive information on glycan structures catalogued from various publications. More information can be found here: https://glycosmos.org/glycomeatlas."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression GlycomeAtlas","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["GlycomeAtlas","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_glycomeatlas.csv","filename":"mouse_proteoform_glycosylation_sites_glycomeatlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_glycomeatlas.stat.csv","filename":"mouse_proteoform_glycosylation_sites_glycomeatlas.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":414,"last_update":"2025-06-03T17:19:07.894113Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001412/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001412/DRAFT","spec_version":"1.3.0","etag":"a2e7f3445605c2d2da02874bd65f20832261f7680677b33b33804cb04609b22f","provenance_domain":{"name":"Human Glycosylation Sites and Glycans (PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-07-18T14:47:24","modified":"2026-01-30T11:15:36.816Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites and Glycans (PDB) dataset contains Homo sapiens [taxid:9606] glycosylation sites and associated glycans provided by the Worldwide Protein Data Bank (wwPDB). PDB data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to wwPDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"human_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"human_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":619,"last_update":"2026-01-30T11:15:36.816429Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001413/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001413/DRAFT","spec_version":"1.3.0","etag":"cc7b5fbe33460e82426454ba2bc15c6ba7e0eda92a62a7664ef8c351ffa154e0","provenance_domain":{"name":"Zebrafish Protein Diseases","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-07-18T16:54:58.662Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Protein Diseases contains diseases associated with Danio rerio [taxid:7955] protein UniProtKB canonical accessions. The dataset also contains mapping of UniProtKB canonical accessions to the Disease Ontology (DO), Mondo and OMIM resources.\nIf you use this dataset please provide proper attribution to GlyGen and Alliance of Genome Resources."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[]}],"keywords":["disease","zebrafish","mim","do","mondo"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_disease_alliance_genome.csv","filename":"zebrafish_protein_disease_alliance_genome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_disease_alliance_genome.stat.csv","filename":"zebrafish_protein_disease_alliance_genome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":431,"last_update":"2025-07-18T16:54:58.662225Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001414/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001414/DRAFT","spec_version":"1.3.0","etag":"adc078a2b80b452332298ebac742e6b5a420bbb0d87ab5754718a6952988d48f","provenance_domain":{"name":"Bovine IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-07-29T17:06:28.641Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Bovine epitope IEDB dataset contains Bos taurus [taxid:9913] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_iedb.csv","filename":"bovine_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_iedb.stat.csv","filename":"bovine_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":510,"last_update":"2025-07-29T17:06:28.641454Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001415/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001415/DRAFT","spec_version":"1.3.0","etag":"ed262bf70e524483db0fa23ea5920bb5e2747c2508f3e5c67bb89cff43831af8","provenance_domain":{"name":"Bovine UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Bovine UniProtKB Xref IEDB dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_iedb.csv","filename":"bovine_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_iedb.stat.csv","filename":"bovine_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":504,"last_update":"2025-07-29T17:04:11.284029Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001416/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001416/DRAFT","spec_version":"1.3.0","etag":"da1d65925b1b9ba4dc8ab1e8df4754f14cac1e0973c97fffc28e4bbc10053f12","provenance_domain":{"name":"Bovine Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-07-30T11:33:21.171Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Bovine Protein Citations (IEDB) dataset contains Bos taurus [taxid:9913] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","PubMed","IEDB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_iedb.csv","filename":"bovine_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_iedb.stat.csv","filename":"bovine_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":594,"last_update":"2025-07-30T11:33:21.171775Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001417/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001417/DRAFT","spec_version":"1.3.0","etag":"bd71fbcf3c6ae6977d311f02a058cf2d7307aeadefe5cfef9dcf582ef2133c28","provenance_domain":{"name":"Chicken IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Chicken epitope IEDB dataset contains Gallus gallus [taxid:9031] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_iedb.csv","filename":"chicken_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_iedb.stat.csv","filename":"chicken_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":515,"last_update":"2025-07-30T11:13:08.186815Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001418/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001418/DRAFT","spec_version":"1.3.0","etag":"0b9f356daf7f757b52626f997ec3ce753469fd975f8f50222cf493bc411e3039","provenance_domain":{"name":"Chicken UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Chicken UniProtKB Xref IEDB dataset contains Gallus gallus [taxid:9031] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_iedb.csv","filename":"chicken_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_iedb.stat.csv","filename":"chicken_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":509,"last_update":"2025-07-30T11:21:19.756895Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001419/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001419/DRAFT","spec_version":"1.3.0","etag":"8a153bbc62e76a25e0c4c53a24babef18e497bf21f44232daa6241fe60af6d0d","provenance_domain":{"name":"Chicken Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Chicken Protein Citations (IEDB) dataset contains Gallus gallus [taxid:9031] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_iedb.csv","filename":"chicken_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_iedb.stat.csv","filename":"chicken_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":599,"last_update":"2025-07-30T11:36:16.432137Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001420/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001420/DRAFT","spec_version":"1.3.0","etag":"0a1da623bb1c9e82898d85cfd10f2b7a923f37b17cf13757932eaa2fa0be386b","provenance_domain":{"name":"Human IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Human epitope IEDB dataset contains Homo sapiens [taxid:9606] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_iedb.csv","filename":"human_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_iedb.stat.csv","filename":"human_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":511,"last_update":"2025-07-30T11:40:07.550007Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001421/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001421/DRAFT","spec_version":"1.3.0","etag":"a609adbb12db274bfca923777be6b82354aecbc55958a4f44a310daa541a5bb4","provenance_domain":{"name":"Human UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Human UniProtKB Xref IEDB dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_iedb.csv","filename":"human_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_iedb.stat.csv","filename":"human_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":505,"last_update":"2025-07-30T11:42:28.295882Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001422/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001422/DRAFT","spec_version":"1.3.0","etag":"118403f4df84890a63c455b036421921da788e34c830da012c4c391c54566a3d","provenance_domain":{"name":"Human Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Human Protein Citations (IEDB) dataset contains Homo sapiens [taxid:9606] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_iedb.csv","filename":"human_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_iedb.stat.csv","filename":"human_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":595,"last_update":"2025-07-30T11:44:45.628791Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001423/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001423/DRAFT","spec_version":"1.3.0","etag":"de0f0450cf4abcb7e21710a1c4f9c14b641c0fccb2ddc924d1c27e5e8a45839d","provenance_domain":{"name":"Mouse IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Mouse epitope IEDB dataset contains Mus musculus [taxid:10090] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_iedb.csv","filename":"mouse_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_iedb.stat.csv","filename":"mouse_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":512,"last_update":"2025-07-30T11:48:16.077763Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001424/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001424/DRAFT","spec_version":"1.3.0","etag":"54e838367983d1cc827f83cf4f25e9ffe3afe4de387754138752488137f8bc7a","provenance_domain":{"name":"Mouse UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Mouse UniProtKB Xref IEDB dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_iedb.csv","filename":"mouse_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_iedb.stat.csv","filename":"mouse_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":506,"last_update":"2025-07-30T11:50:12.134562Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001425/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001425/DRAFT","spec_version":"1.3.0","etag":"291f947ed209406ec1a4cb00aa92ec0229a9c992d80867f7b3c1a4623afcf768","provenance_domain":{"name":"Mouse Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Mouse Protein Citations (IEDB) dataset contains Mus musculus [taxid:10090] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_iedb.csv","filename":"mouse_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_iedb.stat.csv","filename":"mouse_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":596,"last_update":"2025-07-30T13:05:24.476555Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001426/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001426/DRAFT","spec_version":"1.3.0","etag":"ab40b090af9508e70afc87934e4b6245577b2d144af33097988b00cb99e34e3c","provenance_domain":{"name":"Rat IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Rat epitope IEDB dataset contains Rattus norvegicus [taxid:10116] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_iedb.csv","filename":"rat_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_iedb.stat.csv","filename":"rat_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":516,"last_update":"2025-07-30T13:14:12.983190Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001427/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001427/DRAFT","spec_version":"1.3.0","etag":"9e95388e3e7cb73e8b84e59d58a37d1575500be9d90ce3ba1b1aa81c364a91b5","provenance_domain":{"name":"Rat UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Rat UniProtKB Xref IEDB dataset contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_iedb.csv","filename":"rat_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_iedb.stat.csv","filename":"rat_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":510,"last_update":"2025-07-30T13:14:48.697585Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001428/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001428/DRAFT","spec_version":"1.3.0","etag":"00410c98bb57626a0a1ba0d03aed9df16bc936b207d2a89ef65edc21b5f5ba23","provenance_domain":{"name":"Rat Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Rat Protein Citations (IEDB) dataset contains Rattus norvegicus [taxid:10116] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_iedb.csv","filename":"rat_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_iedb.stat.csv","filename":"rat_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":600,"last_update":"2025-07-30T13:15:14.257318Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001429/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001429/DRAFT","spec_version":"1.3.0","etag":"ba731836e6287ae4a966139cd6d1966716ba6caac7d829f13bea28ec0475c765","provenance_domain":{"name":"Yeast IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Yeast epitope IEDB dataset contains Saccharomyces cerevisiae S288C [taxid:559292] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_iedb.csv","filename":"yeast_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_iedb.stat.csv","filename":"yeast_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":535,"last_update":"2025-07-30T13:21:37.855797Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001430/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001430/DRAFT","spec_version":"1.3.0","etag":"eee2a80673620012c0fd12aa5c2b4788dfc506f24901890052a0ee48eb24634c","provenance_domain":{"name":"Yeast UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Yeast UniProtKB Xref IEDB dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_iedb.csv","filename":"yeast_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_iedb.stat.csv","filename":"yeast_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":529,"last_update":"2025-07-30T13:22:06.521311Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001431/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001431/DRAFT","spec_version":"1.3.0","etag":"71598fa28ceb6959a96296b0ce86c8aa86532867f7eb9d10a656d919945e6ac0","provenance_domain":{"name":"Yeast Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Yeast Protein Citations (IEDB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_iedb.csv","filename":"yeast_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_iedb.stat.csv","filename":"yeast_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":619,"last_update":"2025-07-30T13:22:33.035825Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001432/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001432/DRAFT","spec_version":"1.3.0","etag":"2e03e620335d2744de9d735d3968fd34fa697707f1c7695f5c2b5bcfbb10f5e9","provenance_domain":{"name":"Pig IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Pig epitope IEDB dataset contains Sus scrofa [taxid:9823] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_iedb.csv","filename":"pig_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_iedb.stat.csv","filename":"pig_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":506,"last_update":"2025-07-30T13:29:22.490309Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001433/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001433/DRAFT","spec_version":"1.3.0","etag":"b7953c49e37dd49c007bf8f84242dd56360fc66ed197206ef7d00d4f065ac3fc","provenance_domain":{"name":"Pig UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Pig UniProtKB Xref IEDB dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_iedb.csv","filename":"pig_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_iedb.stat.csv","filename":"pig_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":500,"last_update":"2025-07-30T13:29:49.680960Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001434/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001434/DRAFT","spec_version":"1.3.0","etag":"d32693487d05b3bb5c83c19822865763adb32d3485adc9087156d50efc298f14","provenance_domain":{"name":"Pig Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Pig Protein Citations (IEDB) dataset contains Sus scrofa [taxid:9823] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_iedb.csv","filename":"pig_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_iedb.stat.csv","filename":"pig_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":590,"last_update":"2025-07-30T13:30:14.113817Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001435/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001435/DRAFT","spec_version":"1.3.0","etag":"dad27b4062497816c9bf9ac04239594d8168d60a567cb8c0b83769a01c95613d","provenance_domain":{"name":"Zebrafish IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Zebrafish epitope IEDB dataset contains Danio rerio [taxid:7955] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_iedb.csv","filename":"zebrafish_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_iedb.stat.csv","filename":"zebrafish_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":515,"last_update":"2025-07-30T13:36:01.150941Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001436/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001436/DRAFT","spec_version":"1.3.0","etag":"438fb76240ea25d62b76bb80b1350004e777243fa7b1416f37c579f52523cf46","provenance_domain":{"name":"Zebrafish UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Zebrafish UniProtKB Xref IEDB dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_iedb.csv","filename":"zebrafish_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_iedb.stat.csv","filename":"zebrafish_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":509,"last_update":"2025-07-30T13:36:30.648255Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001437/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001437/DRAFT","spec_version":"1.3.0","etag":"9db7056c1d705d6f3bc52fbb292c0a80aaf2ad1192924f9009d85a01cb27445f","provenance_domain":{"name":"Zebrafish Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Zebrafish Protein Citations (IEDB) dataset contains Danio rerio [taxid:7955] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_iedb.csv","filename":"zebrafish_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_iedb.stat.csv","filename":"zebrafish_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":599,"last_update":"2025-07-30T13:36:55.651554Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001438/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001438/DRAFT","spec_version":"1.3.0","etag":"15c7b1881a4c167d2e53fae7666d98b6a34bb68d2a8ec72fcbafdc44c9ee94a4","provenance_domain":{"name":"Arabidopsis IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Arabidopsis epitope IEDB dataset contains Arabidopsis thaliana [taxid:3702] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_iedb.csv","filename":"arabidopsis_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_iedb.stat.csv","filename":"arabidopsis_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":528,"last_update":"2025-07-30T13:43:41.854164Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001439/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001439/DRAFT","spec_version":"1.3.0","etag":"65972407dfbce9c37cb5ce7208db044276615ee9a2806e4290d3c35a34c6d0de","provenance_domain":{"name":"Arabidopsis UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Arabidopsis UniProtKB Xref IEDB dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_iedb.csv","filename":"arabidopsis_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_iedb.stat.csv","filename":"arabidopsis_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":522,"last_update":"2025-07-30T13:44:04.165007Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001440/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001440/DRAFT","spec_version":"1.3.0","etag":"0040ae57e8e5774d360ea56170d220b2ee831600b705bc4e5f59b851a4a042ae","provenance_domain":{"name":"Arabidopsis Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The Arabidopsis Protein Citations (IEDB) dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_iedb.csv","filename":"arabidopsis_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_iedb.stat.csv","filename":"arabidopsis_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":612,"last_update":"2025-07-30T13:44:27.322439Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001441/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001441/DRAFT","spec_version":"1.3.0","etag":"52973fa50c16d786f8c664da3d3bff0f5f9150a18ae0fb6af9fee3806dc1c834","provenance_domain":{"name":"Fruit fly IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-07-30T15:30:26.192Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Fruit fly epitope IEDB dataset contains Drosophila melanogaster [taxid:7227] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}],"keywords":["Epitope","IEDB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_iedb.csv","filename":"fruitfly_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_iedb.stat.csv","filename":"fruitfly_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":529,"last_update":"2025-07-30T15:30:26.192711Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001442/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001442/DRAFT","spec_version":"1.3.0","etag":"7b1f6907b2dcb0a0b66afc808c29151e2ca28230b5e70d66af197fc4d42194db","provenance_domain":{"name":"Fruit fly UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-07-30T15:31:52.231Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Fruit fly UniProtKB Xref IEDB dataset contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file."}],"keywords":["Epitope","IEDB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_iedb.csv","filename":"fruitfly_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_iedb.stat.csv","filename":"fruitfly_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":523,"last_update":"2025-07-30T15:31:52.231722Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001443/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001443/DRAFT","spec_version":"1.3.0","etag":"1116272ea85c0c80fddda5178363260545b73d902bbc9b7c05231733cccff25d","provenance_domain":{"name":"Fruit fly Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-07-30T15:32:29.285Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Fruit fly Protein Citations (IEDB) dataset contains Drosophila melanogaster [taxid:7227] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","PubMed","IEDB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_iedb.csv","filename":"fruitfly_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_iedb.stat.csv","filename":"fruitfly_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2025-07-30T15:32:29.285781Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001444/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001444/DRAFT","spec_version":"1.3.0","etag":"3205077c1e3b49499b78e6b1aebb92abf42c4a73223a8113fd8fbce8355dac0f","provenance_domain":{"name":"HCV1a IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The HCV1a epitope IEDB dataset contains Hepatitis C virus (isolate H77) [taxid:63746] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_iedb.csv","filename":"hcv1a_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_iedb.stat.csv","filename":"hcv1a_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":535,"last_update":"2025-07-30T14:15:47.636932Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001445/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001445/DRAFT","spec_version":"1.3.0","etag":"04ddc69a51ea1377535073fdaaf81fa401a079045e552fa37b5bfadbdda49a04","provenance_domain":{"name":"HCV1a UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The HCV1a UniProtKB Xref IEDB dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_xref_iedb.csv","filename":"hcv1a_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_xref_iedb.stat.csv","filename":"hcv1a_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":529,"last_update":"2025-07-30T14:16:16.145013Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001446/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001446/DRAFT","spec_version":"1.3.0","etag":"846a345388bffe2b6e9e1a70e10e73b8d7e4429b307c3b1c84f27e9cd9e81c53","provenance_domain":{"name":"HCV1a Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The HCV1a Protein Citations (IEDB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_citations_iedb.csv","filename":"hcv1a_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_citations_iedb.stat.csv","filename":"hcv1a_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":619,"last_update":"2025-07-30T14:16:37.729668Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001447/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001447/DRAFT","spec_version":"1.3.0","etag":"16480866d40a502385dbefdde15e5ce128d069c5940d1ca47087ec682fffd57e","provenance_domain":{"name":"HCV1b IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The HCV1b epitope IEDB dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_iedb.csv","filename":"hcv1b_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_iedb.stat.csv","filename":"hcv1b_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":541,"last_update":"2025-07-30T14:37:52.617057Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001448/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001448/DRAFT","spec_version":"1.3.0","etag":"35beb79f2b55846a7e79967478f271f915614de10cc7c8c39e99d48f9c3cd884","provenance_domain":{"name":"HCV1b UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The HCV1b UniProtKB Xref IEDB dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_xref_iedb.csv","filename":"hcv1b_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_xref_iedb.stat.csv","filename":"hcv1b_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":535,"last_update":"2025-07-30T14:38:18.477618Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001449/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001449/DRAFT","spec_version":"1.3.0","etag":"dc6e362efd993322e02ae0b072e1658f3db30e4627b7da196fb8abb989d20eb4","provenance_domain":{"name":"HCV1b Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The HCV1b Protein Citations (IEDB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_citations_iedb.csv","filename":"hcv1b_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_citations_iedb.stat.csv","filename":"hcv1b_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":625,"last_update":"2025-07-30T14:38:41.848676Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001450/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001450/DRAFT","spec_version":"1.3.0","etag":"9be8f62c23fdb80a6a90750ce4279ebb65f50be1b97f7e63ea6caafe37748abe","provenance_domain":{"name":"SARS-CoV-2 IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The SARS-CoV-2 epitope IEDB dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_iedb.csv","filename":"sarscov2_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_iedb.stat.csv","filename":"sarscov2_protein_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":563,"last_update":"2025-07-30T15:43:45.072042Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001451/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001451/DRAFT","spec_version":"1.3.0","etag":"1d13a799b52b8af819806dfeab41585e90f7fe6534726da886ccdc566ddc0a18","provenance_domain":{"name":"SARS-CoV-2 UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The SARS-CoV-2 UniProtKB Xref IEDB dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_xref_iedb.csv","filename":"sarscov2_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_xref_iedb.stat.csv","filename":"sarscov2_protein_xref_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":557,"last_update":"2025-07-30T15:44:22.619965Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001452/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001452/DRAFT","spec_version":"1.3.0","etag":"9a67dda3312c90e5ab553957e510b97e83d879629082321185381ac04f9c8f6a","provenance_domain":{"name":"SARS-CoV-2 Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","derived_from":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"review":[]},"usability_domain":["The SARS-CoV-2 Protein Citations (IEDB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_iedb.csv","filename":"sarscov2_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_iedb.stat.csv","filename":"sarscov2_protein_citations_iedb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"maria.kim","authorized_users":null,"state":"DRAFT","score":647,"last_update":"2025-07-30T15:44:44.861648Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001453/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001453/DRAFT","etag":"715411c390209db74f38fe07c4f1d0bda1e6725bcbd569a0de602041a1141a4f","spec_version":"1.3.0","provenance_domain":{"name":"Human Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Homo sapiens [TaxID: 9606]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"human_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2025-07-30T20:24:16.991123Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001454/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001454/DRAFT","spec_version":"1.3.0","etag":"8c2c985b301836f6ecc01f53a0569ec17e967e69a1881cb35f464654b957db86","provenance_domain":{"name":"Human Glycan GlycomeAtlas Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycan GlycomeAtlas Citations dataset comprises human [TaxID: 9606] tissue glycan citation information for Homo sapiens. This data is provided by the GlycomeAtlas from GlyCosmos which provides comprehensive information on glycan structures catalogued from various publications. More information can be found here: https://glycosmos.org/glycomeatlas."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["GlycomeAtlas","glycan","proteoform"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_glycomeatlas.csv","filename":"human_proteoform_citations_glycosylation_sites_glycomeatlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_glycomeatlas.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_glycomeatlas.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"GlycomeAtlas Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":435,"last_update":"2025-07-30T20:30:07.027880Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001455/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001455/DRAFT","spec_version":"1.3.0","etag":"038c4cce637678e2d450a94e8a14fca21522bad92dfe7197f65141574849e1a7","provenance_domain":{"name":"Mouse Glycan GlycomeAtlas Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycan GlycomeAtlas Citations dataset comprises mouse [TaxID: 10090] tissue glycan citation information for Mus musculus. This data is provided by the GlycomeAtlas from GlyCosmos which provides comprehensive information on glycan structures catalogued from various publications. More information can be found here: https://glycosmos.org/glycomeatlas."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["GlycomeAtlas","glycan","proteoform"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_glycosylation_sites_glycomeatlas.csv","filename":"mouse_proteoform_citations_glycosylation_sites_glycomeatlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_citations_glycosylation_sites_glycomeatlas.stat.csv","filename":"mouse_proteoform_citations_glycosylation_sites_glycomeatlas.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"GlycomeAtlas Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":437,"last_update":"2025-07-30T20:35:08.702329Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001456/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001456/DRAFT","spec_version":"1.3.0","etag":"2233d11644108143b1017f6b380ac2a977807d9993df81aedd27282a54a00e82","provenance_domain":{"name":"Zebrafish Glycan GlycomeAtlas Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycan GlycomeAtlas Citations dataset comprises zebrafish [TaxID: 7955] tissue glycan citation information for Danio rerio. This data is provided by the GlycomeAtlas from GlyCosmos which provides comprehensive information on glycan structures catalogued from various publications. More information can be found here: https://glycosmos.org/glycomeatlas."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["GlycomeAtlas","glycan","proteoform"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_glycomeatlas.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_glycomeatlas.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_citations_glycosylation_sites_glycomeatlas.stat.csv","filename":"zebrafish_proteoform_citations_glycosylation_sites_glycomeatlas.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"GlycomeAtlas Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Danio rerio"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":444,"last_update":"2025-07-30T20:39:38.421781Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001457/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001457/DRAFT","spec_version":"","etag":"13177e784f0238de4a6a2fb8da339b47388648d971f258ac9d2d5eddb4f892f6","provenance_domain":{"name":"NCBI Gene Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The NCBI Gene Linkouts dataset contains NCBI Gene IDs with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into three files."],"description_domain":{"pipeline_steps":[]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_ncbi_gene_linkouts_two.csv","filename":"protein_ncbi_gene_linkouts_two.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_ncbi_gene_linkouts_two.stat.csv","filename":"protein_ncbi_gene_linkouts_two.stat.csv"}}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkout","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae S288C"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H77)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Gallus gallus"},{"category_name":"species","category_value":"Bos taurus"},{"category_name":"species","category_value":"Cricetulus griseus"},{"category_name":"species","category_value":"Danio rerio"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":371,"last_update":"2025-07-31T11:56:22.535073Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001458/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001458/DRAFT","spec_version":"","etag":"e99abc7fe1df63d18bf7a9ee0f222d9ad0b16401841f4c6fd067c7f085da3d11","provenance_domain":{"name":"NCBI Gene Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The NCBI Gene Linkouts dataset contains NCBI Gene IDs with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib linkout guidelines where 10277 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into three files."],"description_domain":{"pipeline_steps":[]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_ncbi_gene_linkouts_three.csv","filename":"protein_ncbi_gene_linkouts_three.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_ncbi_gene_linkouts_three.stat.csv","filename":"protein_ncbi_gene_linkouts_three.stat.csv"}}]},"execution_domain":{"script":[],"script_driver":"","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkout","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae S288C"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepatitis C virus (isolate H77)"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"},{"category_name":"species","category_value":"Gallus gallus"},{"category_name":"species","category_value":"Bos taurus"},{"category_name":"species","category_value":"Cricetulus griseus"},{"category_name":"species","category_value":"Danio rerio"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":371,"last_update":"2025-07-31T11:59:33.439079Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001459/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001459/DRAFT","spec_version":"1.3.0","etag":"1d5de6ae4481e0ee72da4847815be6bebfc8fbbdbb751e9ef2bbb4bea3f080ca","provenance_domain":{"name":"Human Protein Citations (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-23T16:10:22","modified":"2026-03-23T16:10:35.221Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Human Protein Citations (RCSB PDB) dataset contains Homo sapiens [taxid:9606] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors) and the corresponding RCSB PDB ID and GlyTouCan IDs from file https://data.glygen.org/GLY_001412. If you use this dataset provide proper attribution to RCSB PDB and GlyGen.","RCSB PDB (https://www.rcsb.org) is the US data center for the global Protein Data Bank (PDB) archive of 3D structure data for large biological molecules."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}],"keywords":["PMID","journal","citations","authors","PubMed","RCSB PDB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_rcsb_pdb.csv","filename":"human_proteoform_citations_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_rcsb_pdb.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":626,"last_update":"2026-03-23T16:10:35.221969Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001460/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001460/DRAFT","etag":"38625768bd8fe06db7aced3459cf6032b78f1acaa7a06733bb9707ce726a6f08","provenance_domain":{"name":"Disease Tree","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jonathon Keeney","email":"keeneyjg@gwu.edu"},{"contribution":["contributedBy"],"name":"Not Applicable"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}],"modified":"2025-08-04T07:17:15.253Z"},"usability_domain":["The Disease Tree dataset contains Disease Ontology IDs (DOID) and their disease names mapped to their parent DOIDs and their parent disease names. If you use this dataset please provide proper attribution to DO-KB and GlyGen.","The Disease Ontology Knowledgebase (DO-KB) provides access for exploring integrated disease mechanism and feature knowledge, semantically-defined within the Human Disease Ontology (https://disease-ontology.org)."],"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_disease_tree.csv","filename":"protein_disease_tree.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_disease_tree.stat.csv","filename":"protein_disease_tree.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease Tree","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":528,"last_update":"2025-08-04T07:17:15.253258Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001461/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001461/DRAFT","spec_version":"1.3.0","etag":"706853e67e6d0de538c4698fdb24897fbc81667d0a71cd169fe7e33b41b1e3a1","provenance_domain":{"name":"Human Glycan Tissue Expression TwinsUK","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-09-30T19:14:32.989Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Olga Gornik","affiliation":"University of Zagreb","contribution":["createdBy","curatedBy"],"email":"olga.gornik@gmail.com"},{"name":"Najda Rudman","affiliation":"University of Zagreb","contribution":["createdBy"],"email":"najda.rudman@pharma.unizg.hr"},{"name":"Cristina Menni","affiliation":"TwinsUK","contribution":["createdBy"],"email":"cristina.menni@kcl.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycan Tissue Expression TwinsUK dataset provides glycan tissue expression annotations for Homo sapiens [TaxID: 9606]. The data is provided to GlyGen by Dr. Olga Gornik's team from the University of Zagreb through their collaboration with TwinsUK. Further information can be found here: https://twinsuk.ac.uk/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TwinsUK","glycan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_twinsuk.csv","filename":"human_proteoform_glycosylation_sites_twinsuk.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_twinsuk.stat.csv","filename":"human_proteoform_glycosylation_sites_twinsuk.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TwinsUK","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2025-09-30T19:14:32.989940Z","access_count":7},{"object_id":"https://biocomputeobject.org/GLY_001462/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001462/DRAFT","spec_version":"1.3.0","etag":"48e03d795c33eafc4063823da6db3942f4ab2b6d67125ceb4426064074b59b53","provenance_domain":{"name":"Human Xref HPO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-10-20T10:17:01","modified":"2025-10-20T11:09:00.088Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Human Phenotype Ontology (HPO) xref dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to NCBI gene accessions/identifiers in the HPO database. If you use this dataset please provide proper attribution to GlyGen and HPO.","The HPO database provides a standardized vocabulary of phenotypic abnormalities encountered in human disease."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the HPO genes_to_disease csv file to extract the NCBI gene IDs in HPO and then maps the NCBI IDs to the UniProtKB Canonical accessions."}],"keywords":["HPO","cross-reference","phenotype ontology","disease"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_hpo_gene.csv","filename":"human_protein_xref_hpo_gene.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_hpo_gene.stat.csv","filename":"human_protein_xref_hpo_gene.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"HPO cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":452,"last_update":"2025-10-20T11:09:00.088489Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001463/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001463/DRAFT","spec_version":"1.3.0","etag":"bde23b070049b4807e866a4c6f4088e2ffd4352f7c5a3bcf5f70c3e517aa9af5","provenance_domain":{"name":"Human Disease Xref HPO","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-08-19T13:00:05","modified":"2026-08-24T10:18:38.590Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Human Phenotype Ontology (HPO) xref disease dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to MIM disease accessions/identifiers in the HPO database. If you use this dataset please provide proper attribution to GlyGen and HPO.","The HPO database provides a standardized vocabulary of phenotypic abnormalities encountered in human disease."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the HPO genes_to_disease csv file to extract the MIM disease IDs in HPO and then maps them to the UniProtKB Canonical accessions."}],"keywords":["HPO","cross-reference","phenotype ontology","disease"]},"parametric_domain":[{"value":""}],"io_domain":{"input_subdomain":[{"uri":{"filename":"uniprot-proteome-homo-sapiens.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2025_05_20/uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_disease_xref_hpo.csv","filename":"human_disease_xref_hpo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_disease_xref_hpo.stat.csv","filename":"human_disease_xref_hpo.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"HPO disease cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":464,"last_update":"2026-08-24T10:18:38.590614Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001464/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001464/DRAFT","spec_version":"1.3.0","etag":"cf7119cf63320cba78f72fd4f9b047c62cefab21cc7b0e231e54f270192f7110","provenance_domain":{"name":"Bovine Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:43:42.004Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Bovine Xref iCn3D dataset contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_icn3d.csv","filename":"bovine_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_icn3d.stat.csv","filename":"bovine_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":521,"last_update":"2025-10-20T13:43:42.004780Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001465/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001465/DRAFT","spec_version":"1.3.0","etag":"fb9f0b30918ba07e6d63f0561642a9499a95137c6356e235138e65f9096f8009","provenance_domain":{"name":"Chicken Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:44:50.093Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Chicken Xref iCn3D dataset contains Gallus gallus [taxid:9301] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_icn3d.csv","filename":"chicken_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_icn3d.stat.csv","filename":"chicken_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":525,"last_update":"2025-10-20T13:44:50.093309Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001466/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001466/DRAFT","spec_version":"1.3.0","etag":"535d49db565b82b4bfa773eae1c3814fa73864e77de959f9c65e7c59a4d706e2","provenance_domain":{"name":"Human Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:45:55.898Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Human Xref iCn3D dataset contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_icn3d.csv","filename":"human_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_icn3d.stat.csv","filename":"human_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":522,"last_update":"2025-10-20T13:45:55.898154Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001467/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001467/DRAFT","spec_version":"1.3.0","etag":"94b1cf0897e7f295697c6550520a5f22989419ea44cd1e2d994efec00ec62154","provenance_domain":{"name":"Mouse Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:47:08.932Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Mouse Xref iCn3D dataset contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_icn3d.csv","filename":"mouse_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_icn3d.stat.csv","filename":"mouse_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":523,"last_update":"2025-10-20T13:47:08.932508Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001468/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001468/DRAFT","spec_version":"1.3.0","etag":"227fded08928efc0664a734a7777864de8da34a30a6833012d1d12de68a19f7a","provenance_domain":{"name":"Rat Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:48:28.826Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Rat Xref iCn3D dataset contains Rattus norvegicus [taxid:11106] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_icn3d.csv","filename":"rat_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_icn3d.stat.csv","filename":"rat_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":527,"last_update":"2025-10-20T13:48:28.826620Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001469/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001469/DRAFT","spec_version":"1.3.0","etag":"4750f121106f0aa9ef11a734ca91b248529064177e752d2275579d274b70d7c3","provenance_domain":{"name":"Yeast Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:49:25.612Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Yeast Xref iCn3D dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_icn3d.csv","filename":"yeast_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_icn3d.stat.csv","filename":"yeast_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":546,"last_update":"2025-10-20T13:49:25.612022Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001470/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001470/DRAFT","spec_version":"1.3.0","etag":"2a183cfd5f0b124fdb4dec7d3f3ce3314a3d2752859b85641e951c34ea559292","provenance_domain":{"name":"Pig Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:51:03.369Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Pig Xref iCn3D dataset contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_icn3d.csv","filename":"pig_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_icn3d.stat.csv","filename":"pig_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":517,"last_update":"2025-10-20T13:51:03.369870Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001471/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001471/DRAFT","spec_version":"1.3.0","etag":"35211629aa8dda2c072de58bffdcdca92f7a636145494fcbeca18d15c0f1d3ba","provenance_domain":{"name":"Zebrafish Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:54:56.561Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Zebrafish Xref iCn3D dataset contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_icn3d.csv","filename":"zebrafish_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_icn3d.stat.csv","filename":"zebrafish_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":525,"last_update":"2025-10-20T13:54:56.561649Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001472/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001472/DRAFT","spec_version":"1.3.0","etag":"ee84f62a2b1c658f3f2f228decab1f9ea7b18ecab870bf126f9a0c1b103b59da","provenance_domain":{"name":"Arabidopsis Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-10-20T13:55:19","modified":"2025-10-20T13:55:56.722Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Arabidopsis Xref iCn3D dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_icn3d.csv","filename":"arabidopsis_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_icn3d.stat.csv","filename":"arabidopsis_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":539,"last_update":"2025-10-20T13:55:56.722325Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001473/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001473/DRAFT","spec_version":"1.3.0","etag":"288e1f4f9bd7b8a0c098b1f42ac95ae4d9d29116b35c81cafbf0456b917ff22e","provenance_domain":{"name":"Fruitfly Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:57:08.225Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Fruitfly Xref iCn3D dataset contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_icn3d.csv","filename":"fruitfly_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_icn3d.stat.csv","filename":"fruitfly_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":539,"last_update":"2025-10-20T13:57:08.225462Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001474/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001474/DRAFT","spec_version":"1.3.0","etag":"619142d9359d4b88e29d9fafd374d66b19ab41a92f76e7ac7f5362503bf51a74","provenance_domain":{"name":"Hamster Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:58:19.039Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Hamster Xref iCn3D dataset contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_icn3d.csv","filename":"hamster_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_icn3d.stat.csv","filename":"hamster_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":533,"last_update":"2025-10-20T13:58:19.039703Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001475/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001475/DRAFT","spec_version":"1.3.0","etag":"f53fcc227f1ee12a96766b434a7350e21131523e9bc508bca21bd40522866dae","provenance_domain":{"name":"HCV1a Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T13:59:32.595Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The HCV1a Xref iCn3D dataset contains Hepatitis C virus (isolate H77) UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_xref_icn3d.csv","filename":"hcv1a_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_xref_icn3d.stat.csv","filename":"hcv1a_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":529,"last_update":"2025-10-20T13:59:32.595524Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001476/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001476/DRAFT","spec_version":"1.3.0","etag":"c78771a26e70f08d274561f761135e47f283c990ccf71d0c1702d9fe7836c7dd","provenance_domain":{"name":"HCV1b Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:00:44.282Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The HCV1b Xref iCn3D dataset contains Hepatitis C virus (genotype 1b, isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_xref_icn3d.csv","filename":"hcv1b_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_xref_icn3d.stat.csv","filename":"hcv1b_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis c virus (isolate japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":567,"last_update":"2025-10-20T14:00:44.282042Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001477/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001477/DRAFT","spec_version":"1.3.0","etag":"f49d90b1a1533bcc93a0836dd697d0da236436d03437e5d9efd5d523adc9e067","provenance_domain":{"name":"SARS-CoV1 Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:15:55.955Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Xref iCn3D dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_xref_icn3d.csv","filename":"sarscov1_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_xref_icn3d.stat.csv","filename":"sarscov1_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":602,"last_update":"2025-10-20T14:15:55.955431Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001478/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001478/DRAFT","spec_version":"1.3.0","etag":"1837c7793f853530fecaae1b6dd7a6d5b5ad5f74a6ab4503287c5add428ef032","provenance_domain":{"name":"SARS-CoV2 Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:17:07.326Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Xref iCn3D dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_xref_icn3d.csv","filename":"sarscov2_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_xref_icn3d.stat.csv","filename":"sarscov2_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":612,"last_update":"2025-10-20T14:17:07.326179Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001479/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001479/DRAFT","spec_version":"1.3.0","etag":"65ad1cefb831cb19e740ad6e5a931827dc9bcbe217c326dae5a9495625d148c0","provenance_domain":{"name":"Dicty Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Dicty Xref iCn3D dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["3D structure","iCn3D","cross-reference"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_xref_icn3d.csv","filename":"dicty_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_xref_icn3d.stat.csv","filename":"dicty_protein_xref_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":537,"last_update":"2025-10-20T14:18:06.520575Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001480/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001480/DRAFT","etag":"3a52857e84c7d37c6cf7d6de29ae3d88670e336edb75490cf616d0f93510725f","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Sequences IUPAC Condensed","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:31:31.525156","modified":"2024-05-17T11:23:55.178Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Nathan Edwards","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"nje5@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides the condensed glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Condensed format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa domesticus"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Condensed"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_sequences_iupac_condensed.csv","filename":"glycan_sequences_iupac_condensed.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_sequences_iupac_condensed.stat.csv","filename":"glycan_sequences_iupac_condensed.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":351,"last_update":"2025-10-23T15:26:36.390361Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001481/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001481/DRAFT","etag":"369b6160008d9064bba318830e01666905e1c1c369ac95a0099fa059848749d0","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Sequences IUPAC Compact","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:31:31.525156","modified":"2024-05-17T11:23:55.178Z","embargo":{"start_time":"","end_time":""},"contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Nathan Edwards","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"nje5@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides the compact glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glytoucan.org/"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Compact format","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa domesticus"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Hepacivirus C"},{"category_name":"species","category_value":"Severe acute respiratory syndrome-related coronavirus"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Compact"],"platform":[],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_sequences_iupac_compact.csv","filename":"glycan_sequences_iupac_compact.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_sequences_iupac_compact.stat.csv","filename":"glycan_sequences_iupac_compact.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":349,"last_update":"2025-10-23T15:30:53.323677Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001482/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001482/DRAFT","etag":"cd24ecab2c115ae03da97ceb4ce73a1f35a4cffc737c26dfb1ef7f846221f811","spec_version":"1.3.0","provenance_domain":{"name":"Human Glycan TwinsUK Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycan Tissue Expression TwinsUK Citations dataset provides citation information for glycan tissue expression annotations for Homo sapiens [TaxID: 9606]. This data is provided to us by Dr. Olga Gornik and her lab's collaboration with TwinsUK (https://twinsuk.ac.uk/)."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TwinsUK Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TwinsUK","glycan","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_twinsuk.csv","filename":"human_proteoform_citations_glycosylation_sites_twinsuk.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_citations_glycosylation_sites_twinsuk.stat.csv","filename":"human_proteoform_citations_glycosylation_sites_twinsuk.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":337,"last_update":"2025-11-03T19:27:23.281006Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001483/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001483/DRAFT","spec_version":"1.3.0","etag":"d48c6e3698486f0da6d5f560c177f631e360d42c754a9e62a8c2de2c4e279131","provenance_domain":{"name":"Gene Ontology (GO) Tree","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-11-04T14:48:07","modified":"2026-08-24T12:42:41.934Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Gene Ontology (GO) Tree dataset contains GO term IDs and their GO term names mapped to their parent GO term IDs and their parent GO term names. If you use this dataset please provide proper attribution to Gene Ontology and GlyGen.","The Gene Ontology (GO) is a structured, standardized representation of biological knowledge that describes concepts (also known as terms, or formally, classes) that are connected to each other via formally defined relations (https://geneontology.org)."],"description_domain":{"pipeline_steps":[{"description":"The script maps GO terms to their parent GO terms."}],"keywords":["Gene Ontology","GO","GO terms"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_go_tree.csv","filename":"protein_go_tree.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/protein_go_tree.stat.csv","filename":"protein_go_tree.stat.csv"}}]},"execution_domain":{"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GO Tree","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":587,"last_update":"2026-08-24T12:42:41.934270Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001484/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001484/DRAFT","etag":"a9ec5e8760edacefc39b643e91664461ff9a82eacaaae1f771573721a06c69c9","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:57:18.780Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Cricetulus griseus [TaxID:10029]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Cricetulus griseus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_tablemaker.csv","filename":"hamster_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"hamster_proteoform_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":329,"last_update":"2026-01-20T20:10:12.654156Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001485/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001485/DRAFT","etag":"8d029d14c434e394fd5e2ee0290b195d7788e06b791f27b42adbb66e81002399","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:57:18.780Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Mus musculus [TaxID:10090]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Mus musculus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_tablemaker.csv","filename":"mouse_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"mouse_proteoform_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":319,"last_update":"2026-01-20T20:17:00.674412Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001486/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001486/DRAFT","etag":"9906ff37d8f6eeb23412e5062dad18139cefa76e13218a9fca955e2dbf393c68","spec_version":"1.3.0","provenance_domain":{"name":"Rat Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:57:18.780Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Rattus norvegicus [TaxID:10116]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Rattus norvegicus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_tablemaker.csv","filename":"rat_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"rat_proteoform_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":323,"last_update":"2026-01-20T20:19:56.300717Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001487/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001487/DRAFT","etag":"ca70be0195e35c8d60991569c88e9c1271f4fdd10dc9eab2d49923a7dd4d0e3a","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:57:18.780Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Arabidopsis thaliana [TaxID:3702]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Arabidopsis thaliana"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_glycosylation_sites_tablemaker.csv","filename":"arabidopsis_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":335,"last_update":"2026-01-20T20:24:06.419080Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001488/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001488/DRAFT","etag":"1e4bc088966165db1b82cba4080083735cbfa28f329f15141ffdd818ce7f9d3a","spec_version":"1.3.0","provenance_domain":{"name":"Dicty Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-05-29T15:57:18.780Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Dictyostelium discoideum [TaxID:44689]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Dictyostelium discoideum"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycosylation_sites_tablemaker.csv","filename":"dicty_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"dicty_proteoform_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":333,"last_update":"2026-01-20T23:49:04.953790Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001489/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001489/DRAFT","spec_version":"1.3.0","etag":"1560d94b76472df7022e6c96bad2828ac5cbdcb0d2b99c0fd24a49c3675866f4","provenance_domain":{"name":"Chicken Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-01-21T17:22:13.248Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Gallus gallus [TaxID:9031]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_tablemaker.csv","filename":"chicken_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"chicken_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Gallus gallus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":321,"last_update":"2026-01-21T17:22:13.248440Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001490/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001490/DRAFT","spec_version":"1.3.0","etag":"de662304505d3f4e417c578539651bfd72c96ceab78be8da8ef971f89abae223","provenance_domain":{"name":"Pig Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-03-23T14:50:13.490Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Sus scrofa [TaxID:9823]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_tablemaker.csv","filename":"pig_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"pig_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Sus scrofa"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2026-03-23T14:50:13.490057Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001491/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001491/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"a021e8825b77438de160b34d48d7fc247837400ab8f865e1fb424bf39cd3c9bd","provenance_domain":{"name":"GlycoShape Glycan 3D Data","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-01-21T17:02:22","modified":"2026-02-11T14:48:35.421Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides cross-references to GlycoShape for the associated glycan (GlyTouCan Accession). GlycoShape is an open-access database and toolbox that provides 3D structural information on glycans, allowing researchers to accurately model and add complex sugar chains to protein structures in their native, functional forms. The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoShape cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoShape","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_glycoshape.csv","filename":"glycan_xref_glycoshape.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_glycoshape.stat.csv","filename":"glycan_xref_glycoshape.stat.csv"}}]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":645,"last_update":"2026-02-11T14:48:35.421746Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001492/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001492/DRAFT","spec_version":"1.3.0","etag":"bfdbde807d3a9401368a811333cb4e11f84ad51a11039fce487f82510614ef6f","provenance_domain":{"name":"Rat Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-08-18T14:27:16.820Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycosylation Sites and Glycans (RCSB PDB) dataset contains Rattus norvegicus [taxid:10116] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"rat_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"rat_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":607,"last_update":"2026-08-18T14:27:16.820644Z","access_count":8},{"object_id":"https://biocomputeobject.org/GLY_001493/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001493/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"326815faf2b537b58d59fd1d0f590958fd420f504972ae2f683145757161e2aa","provenance_domain":{"name":"Chicken Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-01-21T17:09:38","modified":"2026-08-18T14:28:07.062Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosylation Sites and Glycans (RCSB PDB) dataset contains Gallus gallus [taxid:9031] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"chicken_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"chicken_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":606,"last_update":"2026-08-18T14:28:07.062159Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001494/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001494/DRAFT","spec_version":"1.3.0","etag":"2d65e319ab590cd5c6e92f4a542fbd3c47d1fc221644983549423b2b27a10b66","provenance_domain":{"name":"Yeast Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-03-23T15:24:57.481Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Saccharomyces cerevisiae S288C [TaxID:559292]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_tablemaker.csv","filename":"yeast_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"yeast_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Saccharomyces cerevisiae S288C"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":342,"last_update":"2026-03-23T15:24:57.481970Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001495/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001495/DRAFT","spec_version":"1.3.0","etag":"1c621526d59643ea8a48691dc47e3d9e6e724bb625dd6fa6b5781a54ba8adcbe","provenance_domain":{"name":"Fruit Fly Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-08-18T14:28:54.470Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruit Fly Glycosylation Sites and Glycans (RCSB PDB) dataset contains Drosophila melanogaster [taxid:7227] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"fruitfly_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":620,"last_update":"2026-08-18T14:28:54.470607Z","access_count":4},{"object_id":"https://biocomputeobject.org/GLY_001496/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001496/DRAFT","spec_version":"1.3.0","etag":"bf8f5468697176bac545ce2bf59be19a1c0f64fa5d507ec08a0d494fc4995906","provenance_domain":{"name":"Yeast Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-08-18T14:29:39.542Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycosylation Sites and Glycans (RCSB PDB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"yeast_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"yeast_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":626,"last_update":"2026-08-18T14:29:39.542285Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001497/DRAFT","contents":{"etag":"51ec9b410df7c84c5b1e4ab0412a31f2ffc012ae98a94b0cae51895a4d598dc2","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-01-21T17:28:54","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Bos taurus [TaxID:9913]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker/."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Bos taurus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","proteoform"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_tablemaker.csv","filename":"bovine_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"bovine_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"error_domain":{},"object_id":"https://biocomputeobject.org/GLY_001497/DRAFT"},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":317,"last_update":"2026-01-21T17:28:57.512861Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001498/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001498/DRAFT","spec_version":"1.3.0","etag":"48cc1d73d127ab4b2cce2d8da24fa80918244b48687d8e1fc3167369dba021ef","provenance_domain":{"name":"Mouse Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-07-18T14:47:24","modified":"2026-08-18T14:31:28.017Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Sites and Glycans (RCSB PDB) dataset contains Mus musculus [taxid:10090] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":603,"last_update":"2026-08-18T14:31:28.017944Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001499/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001499/DRAFT","spec_version":"1.3.0","etag":"9e9f281baedd4eacbeddbfed3de44858cf4e808f171cbc1f1eda22499a80b8d3","provenance_domain":{"name":"Dicty Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-07-18T14:47:24","modified":"2026-08-18T14:32:01.980Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Glycosylation Sites and Glycans (RCSB PDB) dataset contains Dictyostelium discoideum [taxid:44689] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"dicty_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"dicty_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":618,"last_update":"2026-08-18T14:32:01.980251Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001500/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001500/DRAFT","spec_version":"1.3.0","etag":"c4909e5e9eb0dc5867e8864ff799a8b0b5c60a9d7f27a8ba2a921568d7e9b105","provenance_domain":{"name":"Pig Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2025-07-18T14:47:24","modified":"2026-08-18T14:32:44.510Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycosylation Sites and Glycans (RCSB PDB) dataset contains Sus scrofa [taxid:9823] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"pig_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"pig_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":597,"last_update":"2026-08-18T14:32:44.510256Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001501/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001501/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"365ccde89a8431a8bcd784e06f71cf94389b695df728d7aa1de2adecfb885fbd","provenance_domain":{"name":"HCV1a Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://spdx.org/licenses/CC-BY-4.0.html","created":"2026-01-21T19:25:46","modified":"2026-03-23T16:13:55.196Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1a Glycosylation Sites and Glycans (RCSB PDB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"hcv1a_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":626,"last_update":"2026-03-23T16:13:55.196811Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001502/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001502/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"fb57c2567b17935c4d0afcee27189100b29dd78094a774bd577d5a527624f1f0","provenance_domain":{"name":"SARS-CoV-1 Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-01-21T19:31:15","modified":"2026-08-18T14:33:53.514Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV-1 Glycosylation Sites and Glycans (RCSB PDB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"sarscov1_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":660,"last_update":"2026-08-18T14:33:53.514243Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001503/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001503/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"db277255af0ddb97fd4826dc8b7fdc9ed2aae84e927ed5149120cae9db46f323","provenance_domain":{"name":"SARS-CoV-2 Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-01-21T19:35:56","modified":"2026-08-18T14:34:57.078Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV-2 Glycosylation Sites and Glycans (RCSB PDB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"sarscov2_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":654,"last_update":"2026-08-18T14:34:57.078895Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001504/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001504/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"c7b4539aa10ab9c8f583b7402e54677a8bdac232d6f7a22936f34c27861c07b8","provenance_domain":{"name":"Arabidopsis Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://spdx.org/licenses/CC-BY-4.0.html","created":"2026-01-21T19:39:16","modified":"2026-08-18T14:35:47.575Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycosylation Sites and Glycans (RCSB PDB) dataset contains Arabidopsis thaliana [taxid:3702] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"arabidopsis_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":619,"last_update":"2026-08-18T14:35:47.575213Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001505/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001505/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"6841546e3792d8950ac1275cc2325eeacb65223e5ceafea74c918853acd62e8e","provenance_domain":{"name":"Bovine Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-01-21T19:42:36","modified":"2026-08-18T14:36:28.481Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycosylation Sites and Glycans (RCSB PDB) dataset contains Bos taurus [taxid:9913] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"bovine_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"bovine_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":601,"last_update":"2026-08-18T14:36:28.481337Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001506/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001506/DRAFT","spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","etag":"38a7c2feab21bc04aeac86cf64c39286e9db6e0169c4c3ed51087f11b8d51b90","provenance_domain":{"name":"Hamster Glycosylation Sites and Glycans (RCSB PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-01-21T19:45:51","modified":"2026-08-18T14:37:18.771Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycosylation Sites and Glycans (RCSB PDB) dataset contains Cricetulus griseus [taxid:10029] glycosylation sites and associated glycans provided by the RCSB PDB database. Data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to RCSB PDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in three steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"hamster_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"hamster_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2026-08-18T14:37:18.771599Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001507/DRAFT","contents":{"spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"created":"2026-01-22T18:02:32","modified":"2026-01-22T18:02:32.364Z"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{}},"error_domain":{},"object_id":"https://biocomputeobject.org/GLY_001507/DRAFT","etag":"062e691329d6d00226e995fa7b41fe987cd080f6f8af0c3e408e978b91ab92a4"},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2026-01-22T18:14:37.657079Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001508/DRAFT","contents":{"spec_version":"https://w3id.org/ieee/ieee-2791-schema/2791object.json","provenance_domain":{"created":"2026-01-22T18:02:32","modified":"2026-01-22T18:02:32.364Z"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{}},"error_domain":{},"object_id":"https://biocomputeobject.org/GLY_001508/DRAFT","etag":"89aa0f0c3a73039c213c7d853939fd16c87cc05ac121606962273a0b9acdb8c8"},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":0,"last_update":"2026-01-22T18:14:40.597433Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001509/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001509/DRAFT","etag":"7ece3fb8cac9a9d830745fbd721fb17bf1073060e1dc6765921ecb0808a62c0e","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref extended PDB IDs contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb extended cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extednded PDB ID format and extracts the data as a csv dataset.","prerequisite":[],"output_list":[]}],"keywords":["protein 3D structure","PDB","cross-reference"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_pdb_extended.csv","filename":"arabidopsis_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_pdb_extended.stat.csv","filename":"arabidopsis_protein_xref_pdb_extended.stat.csv"}}],"input_subdomain":[{"uri":{"filename":"uniprot-proteome-arabidopsis-thaliana.nt","uri":"https:/data.glygen.org/ln2downloads/ebi/2025_10_01/uniprot-proteome-arabidopsis-thaliana.nt"}}]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":521,"last_update":"2026-03-03T10:43:01.087663Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001510/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001510/DRAFT","spec_version":"1.3.0","etag":"096df8bcd97250eef1354fc709413ed7eedf01fa04fdb716ac8b8f34d935c7db","provenance_domain":{"name":"Arabidopsis UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T10:44:36","modified":"2026-03-03T10:46:53.805Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis UniProtKB Xref extended PDB IDs contains Arabidopsis thaliana [taxid:3702] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_pdb_extended.csv","filename":"arabidopsis_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_xref_pdb_extended.stat.csv","filename":"arabidopsis_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":521,"last_update":"2026-03-03T10:46:53.805173Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001511/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001511/DRAFT","spec_version":"1.3.0","etag":"694d419630ef312ef80dd5e15caf9284241bcaa6e1bb7a7abe16f2ba86986ad1","provenance_domain":{"name":"Human UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T10:48:03","modified":"2026-03-03T10:49:11.747Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human UniProtKB Xref extended PDB IDs contains Homo sapiens [taxid:9606] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_pdb_extended.csv","filename":"human_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_pdb_extended.stat.csv","filename":"human_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":504,"last_update":"2026-03-03T10:49:11.747407Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001512/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001512/DRAFT","spec_version":"1.3.0","etag":"8b82b8126cc85f5b4c264cee5c18bc0a6bf21472990cea558f4115694e40cfac","provenance_domain":{"name":"Bovine UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T10:49:40","modified":"2026-03-03T10:51:40.057Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine UniProtKB Xref extended PDB IDs contains Bos taurus [taxid:9913] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pdb_extended.csv","filename":"bovine_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_xref_pdb_extended.stat.csv","filename":"bovine_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus ","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":503,"last_update":"2026-03-03T10:51:40.057416Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001513/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001513/DRAFT","spec_version":"1.3.0","etag":"d02af07a1f0ca3f1f94c462d81e117182092146e2d1a4e19491712f86ec56160","provenance_domain":{"name":"Mouse UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T10:52:23","modified":"2026-03-03T10:53:33.934Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse UniProtKB Xref extended PDB IDs contains Mus musculus [taxid:10090] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_pdb_extended.csv","filename":"mouse_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_xref_pdb_extended.stat.csv","filename":"mouse_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":505,"last_update":"2026-03-03T10:53:33.934939Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001514/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001514/DRAFT","spec_version":"1.3.0","etag":"a1412be9173e05d32d65ed15c19145d16e9ce95f475750935ebe8a36f6678001","provenance_domain":{"name":"Chicken UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T10:54:19","modified":"2026-03-03T10:55:37.049Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken UniProtKB Xref extended PDB IDs contains Gallus gallus [taxid:9301] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_pdb_extended.csv","filename":"chicken_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_xref_pdb_extended.stat.csv","filename":"chicken_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2026-03-03T10:55:37.049912Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001515/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001515/DRAFT","spec_version":"1.3.0","etag":"423a6b4e07bbd2709b4cf4b8e0dacdfd78a298d4f3f9f7be8386850b3fde8362","provenance_domain":{"name":"Pig UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T10:56:20","modified":"2026-03-03T10:58:39.197Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig UniProtKB Xref extended PDB IDs contains Sus scrofa [taxid:9823] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_pdb_extended.csv","filename":"pig_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_xref_pdb_extended.stat.csv","filename":"pig_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":499,"last_update":"2026-03-03T10:58:39.197984Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001516/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001516/DRAFT","spec_version":"1.3.0","etag":"e1c15c9457d7e714cc786a5bd6d171db78f9dbb3f140b2250d74d784a542de24","provenance_domain":{"name":"Dicty UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T10:58:50","modified":"2026-03-03T10:59:46.969Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty UniProtKB Xref extended PDB IDs contains Dictyostelium discoideum [taxid:44689] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_xref_pdb_extended.csv","filename":"dicty_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_xref_pdb_extended.stat.csv","filename":"dicty_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":519,"last_update":"2026-03-03T10:59:46.969561Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001517/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001517/DRAFT","spec_version":"1.3.0","etag":"7ba0bf77b46333992ff62a5618d2162ae152945217fc0d9abe513de34e1f5dd3","provenance_domain":{"name":"Rat UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:00:51","modified":"2026-03-03T11:01:58.068Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat UniProtKB Xref extended PDB IDs contains Rattus norvegicus [taxid:10116] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_pdb_extended.csv","filename":"rat_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_xref_pdb_extended.stat.csv","filename":"rat_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":509,"last_update":"2026-03-03T11:01:58.068196Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001518/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001518/DRAFT","spec_version":"1.3.0","etag":"dcb867b4fea725171663b5841f4b9eedef499d50c44482a0612606ad99ac732a","provenance_domain":{"name":"Fruitfly UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:02:57","modified":"2026-03-03T11:04:04.200Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly UniProtKB Xref extended PDB IDs contains Drosophila melanogaster [taxid:7227] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pdb_extended.csv","filename":"fruitfly_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pdb_extended.stat.csv","filename":"fruitfly_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":521,"last_update":"2026-03-03T11:04:04.200934Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001519/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001519/DRAFT","spec_version":"1.3.0","etag":"88c57ba5385e88a54c11c1e4496f2de8d13db641e8e05463ef3371e18d49c924","provenance_domain":{"name":"SARS-CoV1 UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:12:52","modified":"2026-03-03T11:14:50.850Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref extended PDB IDs contains Severe acute respiratory syndrome-related coronavirus [taxid:10116] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB.","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_xref_pdb_extended.csv","filename":"sarscov1_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_xref_pdb_extended.stat.csv","filename":"sarscov1_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":582,"last_update":"2026-03-03T11:14:50.850846Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001520/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001520/DRAFT","spec_version":"1.3.0","etag":"e412d724bb5147ae19efca41992876b3191dc1170a24912b0b8c145f231eb8a4","provenance_domain":{"name":"Hamster UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:16:24","modified":"2026-03-03T11:17:21.537Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster UniProtKB Xref extended PDB IDs contains Cricetulus griseus [taxid:10029] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pdb_extended.csv","filename":"hamster_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_xref_pdb_extended.stat.csv","filename":"hamster_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":515,"last_update":"2026-03-03T11:17:21.537872Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001521/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001521/DRAFT","spec_version":"1.3.0","etag":"0b40b6413780a435aca71adfab5f69947177e9b6424c2f858a44ad53c1932d53","provenance_domain":{"name":"SARS-CoV2 UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:18:35","modified":"2026-03-03T11:20:06.891Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref extended PDB IDs contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_xref_pdb_extended.csv","filename":"sarscov2_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_xref_pdb_extended.stat.csv","filename":"sarscov2_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb extended cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":594,"last_update":"2026-03-03T11:20:06.891714Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001522/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001522/DRAFT","spec_version":"1.3.0","etag":"986722faa8f2a9329acd41729c2eb7f4727811e32abc503253f332d24f053a9b","provenance_domain":{"name":"HCV1a UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:21:15","modified":"2026-03-03T11:22:04.567Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1a UniProtKB Xref extended PDB IDs contains Hepatitis C virus (isolate H77) [taxid:63746] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_xref_pdb_extended.csv","filename":"hcv1a_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_xref_pdb_extended.stat.csv","filename":"hcv1a_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":528,"last_update":"2026-03-03T11:22:04.567632Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001523/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001523/DRAFT","spec_version":"1.3.0","etag":"827484bf03a6b2d0c095105444d4be8494cae86065667ed3b70a93ec37a4d45a","provenance_domain":{"name":"Yeast UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:23:39","modified":"2026-03-03T11:24:37.377Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast UniProtKB Xref extended PDB IDs contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_pdb_extended.csv","filename":"yeast_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_xref_pdb_extended.stat.csv","filename":"yeast_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":528,"last_update":"2026-03-03T11:24:37.377902Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001524/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001524/DRAFT","spec_version":"1.3.0","etag":"5b11e1d9bb48d1f5374c8dfd8a27f176c916186f20d7dfa937f12901baf8ba8b","provenance_domain":{"name":"HCV1b UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:26:10","modified":"2026-03-03T11:27:47.217Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref extended PDB IDs contains Hepatitis C virus (isolate Japanese) [taxid:11116] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_xref_pdb_extended.csv","filename":"hcv1b_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_xref_pdb_extended.stat.csv","filename":"hcv1b_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":587,"last_update":"2026-03-03T11:27:47.217424Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001525/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001525/DRAFT","spec_version":"1.3.0","etag":"dcb5e40d809eadf53ff0306d693741620d349b2155486f8e52d69f5d505b9ef9","provenance_domain":{"name":"Zebrafish UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-03-03T11:28:41","modified":"2026-03-03T11:29:47.196Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish UniProtKB Xref extended PDB IDs contains Danio rerio [taxid:7955] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset."}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pdb_extended.csv","filename":"zebrafish_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_xref_pdb_extended.stat.csv","filename":"zebrafish_protein_xref_pdb_extended.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":507,"last_update":"2026-03-03T11:29:47.196101Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001526/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001526/DRAFT","spec_version":"1.3.0","etag":"bc6cd940a903b104808d9ae7c37a0cea663c3895f2427fa9e3c8506d677a0096","provenance_domain":{"name":"UniChem Glycan Linkouts","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-03-03T12:09:03.539Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The UniChem Glycan Linkouts dataset contains glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). The dataset is formatted as per the UniChem submission guidelines."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP. The script also formats the dataset as defined by the UniChem guidelines to generate a tsv dataset."}],"keywords":["UniChem Glycan Linkouts","UniChem","Glycan","GlyTouCan Accession","SMILES Isomeric"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"tsv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_unichem_linkout.tsv","filename":"glycan_unichem_linkout.tsv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_unichem_linkout.stat.csv","filename":"glycan_unichem_linkout.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniChem glycan linkouts","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Sus scrofa domesticus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":453,"last_update":"2026-03-03T12:09:03.539864Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001527/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001527/DRAFT","etag":"4590bdbe5c351fe13052071cbcdc0e4438d8e397d05b24d825484d0b990358d5","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Cricetulus griseus [TaxID: 10029]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Cricetulus griseus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"hamster_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"hamster_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":371,"last_update":"2026-03-23T14:32:59.257029Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001528/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001528/DRAFT","etag":"b8666fb6371bb25f2e045473b9f6c3bac647f1b6b68b311a4082e60468f68b82","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Gallus gallus [TaxID: 9031]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Gallus gallus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"chicken_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"chicken_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2026-03-23T14:37:57.414395Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001529/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001529/DRAFT","etag":"c4f451b457280cbce6d23bd825032f988655f615a19075fbb3441931e5860f1e","spec_version":"1.3.0","provenance_domain":{"name":"Pig Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Sus scrofa [TaxID: 9823]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Sus scrofa"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"pig_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"pig_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":355,"last_update":"2026-03-23T14:41:03.320402Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001530/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001530/DRAFT","etag":"d3587de358286de9dc5c55fb236580ab80b9d8b2c6bed37548686cbf8f9274c7","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Bos taurus [TaxID: 9913]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Bos taurus"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"bovine_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"bovine_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":359,"last_update":"2026-03-23T14:43:50.778539Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001531/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001531/DRAFT","etag":"5c61ab440971e237b20b946f766fd3b10f8d300a48e3e2583ad35de6d11efc1d","spec_version":"1.3.0","provenance_domain":{"name":"Dicty Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Dictyostelium discoideum [TaxID: 44689]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Dictyostelium discoideum"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"dicty_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"dicty_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":375,"last_update":"2026-03-23T14:46:20.046007Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001532/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001532/DRAFT","etag":"2fa4a4129ac5e27d5a236a0282990aafd6f3a536a4eae88e9f1840dedbb0dc15","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Xref GLYCAM","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-14T12:09:00.597068","modified":"2024-05-17T11:23:55.673Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Nathan Edwards","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"nje5@georgetown.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides cross-references to GLYCAM for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). Source database: https://glycam.org/"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Sus scrofa domesticus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GLYCAM","Cross-references"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.10.1/reviewed/glycan_xref_glycam.csv","filename":"glycan_xref_glycam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-2.10.1/reviewed/glycan_xref_glycam.stat.csv","filename":"glycan_xref_glycam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":312,"last_update":"2026-03-23T15:07:54.250132Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001533/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001533/DRAFT","spec_version":"1.3.0","etag":"de314bb9366a60317dda114852978817fbab7677a769d760334d22d34333bf33","provenance_domain":{"name":"All Human Somatic Mutations","version":"v-x.x.x","modified":"2026-03-23T18:08:19.453Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This Human Somatic Mutation dataset contains all Homo sapiens [taxid:9606] somatic mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) somatic mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the somatic (somatic_staus = 1) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}],"keywords":["single-nucleotide variations (nsSNVs)","somatic mutations","dbSNP","disease","ClinVar"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_mutation_somatic_all.csv","filename":"human_protein_mutation_somatic_all.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_mutation_somatic_all.stat.csv","filename":"human_protein_mutation_somatic_all.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":363,"last_update":"2026-03-23T18:08:19.453958Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001534/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001534/DRAFT","spec_version":"1.3.0","etag":"ce2c89eb0d322dd8983b1603a418485b5d8145e66620ff0cd037e44435f5c35f","provenance_domain":{"name":"All Human Germline Mutations","version":"v-x.x.x","modified":"2026-03-23T18:15:22.536Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This Human Germline Mutations dataset contains all Homo sapiens [taxid:9606] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the gernline mutation data (somatic_staus = 0) from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}],"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_mutation_germline_all.csv","filename":"human_protein_mutation_germline_all.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_mutation_germline_all.stat.csv","filename":"human_protein_mutation_germline_all.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":368,"last_update":"2026-03-23T18:15:22.536054Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001535/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001535/DRAFT","spec_version":"1.3.0","etag":"b2b0e90bd7e83204c439c48e0abb33188c1ba3dbd6db9fef62a4ffc38905b2ae","provenance_domain":{"name":"All Mouse Germline Mutations","version":"v-x.x.x","modified":"2026-03-23T18:17:48.070Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This Human Germline Mutations dataset contains all Mus musculus [taxid:10090] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the gernline mutation data (somatic_staus = 0) from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}],"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_mutation_germline_all.csv","filename":"mouse_protein_mutation_germline_all.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_mutation_germline_all.stat.csv","filename":"mouse_protein_mutation_germline_all.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":369,"last_update":"2026-03-23T18:17:48.070760Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001536/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001536/DRAFT","spec_version":"1.3.0","etag":"db1ef668f9208ecdcfd42bf31dba92bff7203448110f389f388fc5efb72d1dbb","provenance_domain":{"name":"All Rat Germline Mutations","version":"v-x.x.x","modified":"2026-03-23T18:20:36.429Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This Rat Germline Mutations dataset contains all Rattus norvegicus [taxid:10116] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the gernline mutation data (somatic_staus = 0) from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}],"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_mutation_germline_all.csv","filename":"rat_protein_mutation_germline_all.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_mutation_germline_all.stat.csv","filename":"rat_protein_mutation_germline_all.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":373,"last_update":"2026-03-23T18:20:36.429948Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001537/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001537/DRAFT","spec_version":"1.3.0","etag":"97adccf5d35954f97646c0fb91f9ea89b7d0acd9e8c3e976e9f288da2bd65909","provenance_domain":{"name":"All Human Cancer Mutations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-07-08T10:23:14","modified":"2026-07-08T10:30:07.409Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Human Cancer Mutation dataset contains all Homo sapiens [taxid:9606] mutation data from the BioMuta database (https://hive.biochemistry.gwu.edu/biomuta). The BioMuta pipeline documentation can be found on the HIVE Lab Wiki: https://hivelab.biochemistry.gwu.edu/wiki/BioMuta_pipeline_README.","The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.","BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.","The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset, please provide proper attribution to BioMuta and GlyGen.","Note that unlike the human_protein_mutation_cancer.csv dataset (GLY_000024), no filters or criteria for inclusion is applied - all mutations are provided.","If there is also a germline mutation reported in dbSNP, the rsid is also shown. Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias"}],"keywords":["single-nucleotide variations (nsSNVs)","cancer mutations","BioMuta","disease"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_mutation_cancer_all.csv","filename":"human_protein_mutation_cancer_all.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_mutation_cancer_all.stat.csv","filename":"human_protein_mutation_cancer_all.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1377,"last_update":"2026-07-08T10:30:07.409704Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001538/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001538/DRAFT","spec_version":"1.3.0","etag":"4bfa3f96866603fb5b6ad38ff0910d3d930ce3972e52f3eced98131a322a9388","provenance_domain":{"name":"Bundibugyo virus (BDBV) Glycan TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-08-18T14:32:39.634Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The BDBV Glycan Tissue Expression TableMaker dataset provides citation information for glycan tissue expression annotations for Bundibugyo virus [TaxID: 565995]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","glycoprotein","Citations"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_tablemaker.csv","filename":"bdbv_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"bdbv_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Bundibugyo virus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":354,"last_update":"2026-08-18T14:32:39.634393Z","access_count":6},{"object_id":"https://biocomputeobject.org/GLY_001539/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001539/DRAFT","spec_version":"1.3.0","etag":"847155deefcbbfbe8bf1e5095b391196e48d504b98ce5b6fb03d2955f9d83208","provenance_domain":{"name":"Zaire ebolavirus (EBOV) Glycan TableMaker ","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-06-11T19:30:15.248Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The EBOV Glycan Tissue Expression TableMaker dataset provides citation information for glycan tissue expression annotations for Zaire ebolavirus (strain Mayinga-76) [TaxID: 128952]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","glycoprotein","Citations"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"ebov_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"ebov_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Zaire ebolavirus (strain Mayinga-76)"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":378,"last_update":"2026-06-11T19:30:15.248814Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001540/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001540/DRAFT","spec_version":"1.3.0","etag":"a3e910cda4c95cd3960f07c7ec66b38d29e4e422916485e4d127424d0466fb0c","provenance_domain":{"name":"Bundibugyo virus (BDBV) Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2025-03-04T15:53:49.509Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bundibugyo virus (BDBV) Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Bundibugyo virus [TaxID: 565995]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan","glycoproteins","Citations"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"bdbv_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"bdbv_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Bundibugyo virus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2026-06-11T19:34:28.590944Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001541/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001541/DRAFT","spec_version":"1.3.0","etag":"d338b5b2d63733316d64a72b741dfa57b504972818c58235859cc22da837b218","provenance_domain":{"name":"Zaire ebolavirus (EBOV) Glycan TableMaker Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2023-03-14T20:00:08.127Z","modified":"2026-08-18T15:24:53.732Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zaire ebolavirus (EBOV) Glycan Tissue Expression TableMaker Citations dataset provides citation information for glycan tissue expression annotations for Zaire ebolavirus (strain Mayinga-76) [TaxID: 128952]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details: https://glygen.ccrc.uga.edu/tablemaker."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["GlyTablemaker","glycan","glycoproteins","Citations"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_citations_glycosylation_sites_tablemaker.csv","filename":"ebov_proteoform_citations_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_citations_glycosylation_sites_tablemaker.stat.csv","filename":"ebov_proteoform_citations_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Zaire ebolavirus (strain Mayinga-76)"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":413,"last_update":"2026-08-18T15:24:53.732465Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001542/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001542/DRAFT","spec_version":"1.3.0","etag":"3db6483b333e8cd69184d081abd0f5fb46cf34aadb40be8c607bcc544efdcce0","provenance_domain":{"name":"Zebrafish Glycosylation Sites and Glycans (PDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-08-05T13:38:39","modified":"2026-08-18T14:37:33.966Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycosylation Sites and Glycans (RCSB PDB) dataset contains Danio rerio [taxid:7955] glycosylation sites and associated glycans provided by the Worldwide Protein Data Bank (wwPDB). PDB data is retrieved using the RCSB PDB Search API (https://search.rcsb.org/#search-api), Data API (https://data.rcsb.org/index.html#data-api) and Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api). If you use this dataset please provide proper attribution to wwPDB and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script retrieves data from RCSB PDB in four steps: (1) their RCSB PDB Search API (https://search.rcsb.org/#search-api) is used to retrieve any PDB structures with glycosylation data for this species, followed by (2) their RCSB PDB Data API (https://data.rcsb.org/index.html#data-api) to retrieve data on the glycosylated structures identified in step one, including data on the PDB glycosite position, GlyTouCan IDs and publications, and then (3) the RCSB PDB Sequence Coordinates Server API (https://sequence-coordinates.rcsb.org/#sequence-coordinates-api) to map the chain glycosites to the full UniProtKB protein sequence. The script then extracts the data from the API responses to create the dataset."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","DOI","GlyTouCan","RCSB PDB","PDB"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_rcsb_pdb.csv","filename":"zebrafish_proteoform_glycosylation_sites_rcsb_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_rcsb_pdb.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_rcsb_pdb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":629,"last_update":"2026-08-18T14:37:33.966528Z","access_count":5},{"object_id":"https://biocomputeobject.org/GLY_001543/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001543/DRAFT","spec_version":"1.3.0","etag":"085ca4af5b82132956cc9b42ccd9937ec35ecc093ed36740cd60b06089ee6a25","provenance_domain":{"name":"Ebola Virus Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:48:18","modified":"2026-08-19T10:12:35.984Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola Virus Predicted O-Glycosylation Sites dataset contains predicted Zaire ebolavirus (strain Mayinga-76) (TaxID: 128952) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"ebov_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":797,"last_update":"2026-08-19T10:12:35.984297Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001544/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001544/DRAFT","spec_version":"1.3.0","etag":"eb86fce48faf675531ae9b494dd41d802b074bb8553c334a8cfe84bf2eaa6172","provenance_domain":{"name":"Bundibugyo Virus Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2024-08-01T15:48:18","modified":"2024-12-05T16:16:44.558Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bundibugyo Virus Predicted O-Glycosylation Sites dataset contains predicted Bundibugyo Virus (TaxID: 565995) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"parametric_domain":[],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"bdbv_proteoform_glycosylation_sites_predicted_isoglyp.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py"}},{"uri":{"filename":"combine_csv.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"3.6.8","uri":{"uri":"https://www.python.org/download/releases/3.6.8/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":779,"last_update":"2026-07-09T17:40:26.763788Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001545/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001545/DRAFT","etag":"944e30d9ea34bd0bc6154402379e378b6fb4c7b1cc51e4c4355a73150791ca95","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Zaire ebolavirus (strain Mayinga-76) [taxid:128952] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_altnames.csv","filename":"ebov_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_altnames.stat.csv","filename":"ebov_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":311,"last_update":"2026-07-28T11:24:54.074210Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001546/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001546/DRAFT","spec_version":"1.3.0","etag":"c5ec9d2ee99c5f365518bdf4e5d4ebb7a19e6be8f8b0488a941c458cbe4f1d29","provenance_domain":{"name":"Ebola (EBOV) (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-07-28T12:31:39","modified":"2026-07-28T12:32:01.326Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Zaire ebolavirus (strain Mayinga-76) [taxid:128952] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}],"keywords":["protein alternative name","UniProtKB"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_altnames.csv","filename":"ebov_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_altnames.stat.csv","filename":"ebov_protein_altnames.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":311,"last_update":"2026-07-28T12:32:01.326702Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001547/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001547/DRAFT","etag":"d652e113e89bc02ce689c9655cdaad2b704479d15e942522cdb436afe7bf43ea","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Canonical (UniProtKB) Sequences dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all ebov canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_canonicalsequences.fasta","filename":"ebov_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_canonicalsequences.stat.csv","filename":"ebov_protein_canonicalsequences.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":341,"last_update":"2026-07-28T11:40:18.537769Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001548/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001548/DRAFT","etag":"52e6d9bdd019ed12741d6adb2eb001cd81830ceeef815d7384344facef276ce3","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":"","created":"","modified":"","review":[],"contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Ebola (EBOV) Protein Citations (IEDB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_iedb.csv","filename":"ebov_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_iedb.stat.csv","filename":"ebov_protein_citations_iedb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":635,"last_update":"2026-07-28T11:40:21.592677Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001549/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001549/DRAFT","etag":"ab42d551a6624addf9995f92a6a8b3a0221e0520efe28e5a2ca9dfada704fecf","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Citations dataset contains publication information for Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_uniprotkb.csv","filename":"ebov_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_uniprotkb.stat.csv","filename":"ebov_protein_citations_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":543,"last_update":"2026-07-28T11:40:24.640456Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001550/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001550/DRAFT","etag":"367fb15ab58fb02f29ea4982f41142ebf57c5700dac7a6712f69a52d71c9e2ca","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Enzyme Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Enzyme Annotation (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_enzyme_annotation_uniprotkb.csv","filename":"ebov_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"ebov_protein_enzyme_annotation_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":425,"last_update":"2026-07-28T11:40:27.688693Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001551/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001551/DRAFT","etag":"a9a823bb6966d937ef9c1665452aad49406ca9dbcc57db0846a6967223824ead","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Function (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Function (UniProtKB) dataset contains biological function annotation for Zaire ebolavirus (strain Mayinga-76) [taxid:128952] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_function_uniprotkb.csv","filename":"ebov_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_function_uniprotkb.stat.csv","filename":"ebov_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":353,"last_update":"2026-07-28T11:40:30.735191Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001552/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001552/DRAFT","etag":"358c840e017782a2baaa34fa7a739b103c030fadd4b27069d49b2ce6edda417e","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Zaire ebolavirus (strain Mayinga-76) [taxid:128952] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_genenames_uniprotkb.csv","filename":"ebov_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_genenames_uniprotkb.stat.csv","filename":"ebov_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":528,"last_update":"2026-07-28T11:40:33.784785Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001553/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001553/DRAFT","etag":"88d838ea3d682431a065e7a23eb56f4bdd644f163b6a4a50acd98c643e555a39","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) N-Glycosylation Sequon","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_glycosylation_motifs.csv","filename":"ebov_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_glycosylation_motifs.stat.csv","filename":"ebov_protein_glycosylation_motifs.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":449,"last_update":"2026-07-28T11:40:36.837238Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001554/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001554/DRAFT","etag":"a22818237812bd48b263cbc800c5820b280abbad2990bf356dab6627455ea856","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Gene Ontology (GO) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_go_annotation.csv","filename":"ebov_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_go_annotation.stat.csv","filename":"ebov_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":360,"last_update":"2026-07-28T11:40:39.887394Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001555/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001555/DRAFT","etag":"6b6fca2a7cbd23072aa6e17058ae3a696a1de01f8ccff09a0637466610ff9501","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":"","created":"","modified":"","review":[],"contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Ebola (EBOV) epitope IEDB dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_iedb.csv","filename":"ebov_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_iedb.stat.csv","filename":"ebov_protein_iedb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":551,"last_update":"2026-07-28T11:40:42.936565Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001556/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001556/DRAFT","etag":"ae8dc20eea22318a604da3b73de2f3323a15f2b257f0954eee7305c0b949ba3a","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Information (NCBI RefSeq) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_info_refseq.csv","filename":"ebov_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_info_refseq.stat.csv","filename":"ebov_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":389,"last_update":"2026-07-28T11:40:45.982211Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001557/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001557/DRAFT","etag":"b63b5984c99f76be018f62a617f534360bf29babe336b89313277e08b83d8399","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Information dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_info_uniprotkb.csv","filename":"ebov_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_info_uniprotkb.stat.csv","filename":"ebov_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":380,"last_update":"2026-07-28T11:40:49.029537Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001558/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001558/DRAFT","etag":"bcb163f349523537fcb3a669828a830f77f83e8a0814485ce45a3a8d5ac8a0d4","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Proteome Masterlist (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Proteome Masterlist dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_masterlist.csv","filename":"ebov_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_masterlist.stat.csv","filename":"ebov_protein_masterlist.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":395,"last_update":"2026-07-28T11:40:52.078201Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001559/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001559/DRAFT","etag":"5fd17e31dd0da0ce3fe4a8ac3d54dc9de52741e64792d5c2a2dce987ad855bb5","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) EBI-UniProtKB NT file contains proteome data for Zaire ebolavirus (strain Mayinga-76) [taxid:128952] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","version":"","step_number":0,"input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_ntdata.nt","filename":"ebov_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_ntdata.stat.csv","filename":"ebov_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":368,"last_update":"2026-07-28T11:40:55.127938Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001560/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001560/DRAFT","etag":"017c3f1fbbcdc6d245891f6c5891df3d6e65943c502817dd956c46d2373c32b1","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Names (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Names (NCBI RefSeq) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_proteinnames_refseq.csv","filename":"ebov_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_proteinnames_refseq.stat.csv","filename":"ebov_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2026-07-28T11:40:58.174632Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001561/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001561/DRAFT","etag":"25b470a5f5fdd24f747ab3ac1c5afc2d4b0b436889365dcb7d49767f4fce6fd1","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein PTM Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein PTM Annotation (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_ptm_annotation_uniprotkb.csv","filename":"ebov_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_ptm_annotation_uniprotkb.stat.csv","filename":"ebov_protein_ptm_annotation_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":417,"last_update":"2026-07-28T11:41:01.221168Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001562/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001562/DRAFT","etag":"2eb09f5da3f6a7c7288998a8feb27c88d9a74762f5bdc31d20ad2a7909d72586","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Recommended Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Recommended Names (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952]  UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_recnames.csv","filename":"ebov_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_recnames.stat.csv","filename":"ebov_protein_recnames.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2026-07-28T11:41:04.267146Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001563/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001563/DRAFT","etag":"5df1fc495219b9a3f09c1b06697090a0fb2321a64280001d676749f7f1c3d020","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Sequence Info (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Sequence Info (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all ebov isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_sequenceinfo.csv","filename":"ebov_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_sequenceinfo.stat.csv","filename":"ebov_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":371,"last_update":"2026-07-28T11:41:07.315691Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001564/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001564/DRAFT","etag":"3c59295a43d6215ed95f5cb7f5390128ba9c950f095fddadeb8ceb865ade033c","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Signal Peptide","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Signal Peptide dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_annotation.csv","filename":"ebov_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_peptidesequences.fasta","filename":"ebov_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_cleavedsequences.fasta","filename":"ebov_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_fullsequences.fasta","filename":"ebov_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_annotation.stat.csv","filename":"ebov_protein_signalp_annotation.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_peptidesequences.stat.csv","filename":"ebov_protein_signalp_peptidesequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_cleavedsequences.stat.csv","filename":"ebov_protein_signalp_cleavedsequences.stat.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_signalp_fullsequences.stat.csv","filename":"ebov_protein_signalp_fullsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":864,"last_update":"2026-07-28T11:41:10.363645Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001565/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001565/DRAFT","etag":"115d5c6d41bb50b319c060d5d80678520da7a0a1998dfc0926ebcf9250eef3a1","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Site Annotation","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Site Annotation (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_site_annotation_uniprotkb.csv","filename":"ebov_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_site_annotation_uniprotkb.stat.csv","filename":"ebov_protein_site_annotation_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":417,"last_update":"2026-07-28T11:41:13.413539Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001566/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001566/DRAFT","etag":"7a8292e87905fcc136a7d0373f028c254ea48242525cdb76eb015384cfc6d41f","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref NCBI Gene","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) UniProtKB Xref NCBI Gene dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_geneid.csv","filename":"ebov_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_geneid.stat.csv","filename":"ebov_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":649,"last_update":"2026-07-28T11:41:16.461798Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001567/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001567/DRAFT","etag":"3df0ae9fe8ddcf50ee8ca1da8529c33aeaa3168786be348b45d845f4aadb03ec","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Xref iCn3D dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["3D structure","iCn3D","cross-reference"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_icn3d.csv","filename":"ebov_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_icn3d.stat.csv","filename":"ebov_protein_xref_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":561,"last_update":"2026-07-28T11:41:19.510833Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001568/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001568/DRAFT","etag":"3f70022d4e86637e9b4f2ae2a981b7e63c7df4cbf61fecc2435364c5adb50341","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":"","created":"","modified":"","review":[],"contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Ebola (EBOV) UniProtKB Xref IEDB dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_iedb.csv","filename":"ebov_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_iedb.stat.csv","filename":"ebov_protein_xref_iedb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":545,"last_update":"2026-07-28T11:41:22.559312Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001569/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001569/DRAFT","etag":"1e41755b76935f811032d6bb1fd817b374e7125871def8ba84c0b3129da81562","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) UniProtKB Xref InterPro contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_interpro.csv","filename":"ebov_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_interpro.stat.csv","filename":"ebov_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":600,"last_update":"2026-07-28T11:41:25.607919Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001570/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001570/DRAFT","etag":"c97677400acbd3e35806ac2a09902470d4763860cff048a37759a28313a3d1dc","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) UniProtKB Xref PDB contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_pdb.csv","filename":"ebov_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_pdb.stat.csv","filename":"ebov_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":511,"last_update":"2026-07-28T11:41:28.657456Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001571/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001571/DRAFT","etag":"5186cd1fe80e263e3d02f935a6f9872232a114ad410d0defe7d6e01aeb71a362","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) UniProtKB Xref extended PDB IDs contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset.","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_pdb_extended.csv","filename":"ebov_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_pdb_extended.stat.csv","filename":"ebov_protein_xref_pdb_extended.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":543,"last_update":"2026-07-28T11:41:31.705193Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001572/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001572/DRAFT","etag":"a0acbf799aaaa850a0c98217bacabb6c1469b690097383cc81a72f06f3af9a8b","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref Pfam","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) UniProtKB Xref Pfam contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_pfam.csv","filename":"ebov_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_pfam.stat.csv","filename":"ebov_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":510,"last_update":"2026-07-28T11:41:34.755787Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001573/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001573/DRAFT","etag":"5242edf6966bf420e66c5c44612baad6fd2c2d5b7c42040d898eb91f505466d7","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) UniprotKB Xref RefSeq contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_refseq.csv","filename":"ebov_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_refseq.stat.csv","filename":"ebov_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":807,"last_update":"2026-07-28T11:41:37.804526Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001574/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001574/DRAFT","etag":"706dd6041fc5022c7b323811081fc3b671801d3b36eea99403aef9960462091c","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) UniProtKB Xref (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) UniProtKB Xref (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_uniprotkb.csv","filename":"ebov_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_uniprotkb.stat.csv","filename":"ebov_protein_xref_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":349,"last_update":"2026-07-28T11:41:40.852185Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001575/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001575/DRAFT","spec_version":"1.3.0","etag":"60077118ddbf59ac6ba5cbfb8d0d24aa6e17fb97b369736cf0224a49593f9050","provenance_domain":{"name":"Ebola (EBOV) Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-08-19T10:04:38","modified":"2026-08-19T10:09:31.490Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Predicted O-Glycosylation Sites dataset contains predicted Zaire ebolavirus (strain Mayinga-76) (TaxID:128952) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"ebov_proteoform_glycosylation_sites_predicted_isoglyp.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv","filename":"ebov_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}},{"uri":{"filename":"combine_csv.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":797,"last_update":"2026-08-19T10:09:31.490573Z","access_count":3},{"object_id":"https://biocomputeobject.org/GLY_001576/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001576/DRAFT","etag":"9fd673bd96670c6cad94ec13f59cecfe08abeef6d0c9cd929a3af3c790ea615e","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Glycan Tissue Expression TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Zaire ebolavirus (strain Mayinga-76) [TaxID: 128952]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details can be found here: https://glygen.ccrc.uga.edu/tablemaker/."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Zaire ebolavirus (strain Mayinga-76)"}]}}],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[],"prerequisite":[],"output_list":[]}],"keywords":["TableMaker","glycan"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_glycosylation_sites_tablemaker.csv","filename":"ebov_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"ebov_proteoform_glycosylation_sites_tablemaker.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":380,"last_update":"2026-07-28T11:41:46.944213Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001577/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001577/DRAFT","spec_version":"1.3.0","etag":"36a84371ff343a110b15b3a8fc79d2ff27e38ac6bf046db295161b902daee922","provenance_domain":{"name":"Ebola (EBOV) Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Glycosylation Sites (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [TaxID:128952] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Zaire ebolavirus (strain Mayinga-76) proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_glycosylation_sites_uniprotkb.csv","filename":"ebov_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"ebov_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":402,"last_update":"2026-07-28T11:41:49.990065Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001578/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001578/DRAFT","etag":"97f4d2d918e996e3844e0777138fec13d4ad896f333745acbca5837210dcb270","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Phosphorylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Phosphorylation Sites (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [TaxID:128952] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"ebov_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"ebov_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":415,"last_update":"2026-07-28T11:41:53.037970Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001579/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001579/DRAFT","etag":"ef0636d1da47452f2783ce9bd4b93f1fea6a89c02a7cce71d21683b540e63321","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Alternative Name (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for Bundibugyo virus [taxid:565995] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_altnames.csv","filename":"bdbv_protein_altnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_altnames.stat.csv","filename":"bdbv_protein_altnames.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":287,"last_update":"2026-07-28T11:42:14.123021Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001580/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001580/DRAFT","etag":"6b18f083d48a4d717e579556aef73243eb745a608bb6b665ccaa534f322e7f8f","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Canonical sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Canonical (UniProtKB) Sequences dataset contains Bundibugyo virus [taxid:565995] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB fasta sequence for all bdbv canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_canonicalsequences.fasta","filename":"bdbv_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_canonicalsequences.stat.csv","filename":"bdbv_protein_canonicalsequences.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":317,"last_update":"2026-07-28T11:42:17.174205Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001581/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001581/DRAFT","etag":"1c6199403f3e9aec2877e8196c1241ef22d689a69eb7ac60513a8ae8d64679f1","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Citations (IEDB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":"","created":"","modified":"","review":[],"contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Ebola (BDBV) Protein Citations (IEDB) dataset contains Bundibugyo virus [taxid:565995] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors, and the corresponding IEDB accession). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["PMID","journal","citations","authors","PubMed","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs.","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_citations_iedb.csv","filename":"bdbv_protein_citations_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_citations_iedb.stat.csv","filename":"bdbv_protein_citations_iedb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":611,"last_update":"2026-07-28T11:42:20.221866Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001582/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001582/DRAFT","etag":"6e286f6b7d48511714ec94b8733e6a3e88be806841487877c96ae92842b11d9a","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Citations dataset contains publication information for Bundibugyo virus [taxid:565995] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_citations_uniprotkb.csv","filename":"bdbv_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_citations_uniprotkb.stat.csv","filename":"bdbv_protein_citations_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":519,"last_update":"2026-07-28T11:42:23.268278Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001583/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001583/DRAFT","etag":"baae57dcbed00a9f1c0c92e262dc7f2e57cc2194751020affdf8cc99df13e827","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Enzyme Annotation (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Enzyme Annotation (UniProtKB) dataset contains Bundibugyo virus [taxid:565995] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_enzyme_annotation_uniprotkb.csv","filename":"bdbv_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"bdbv_protein_enzyme_annotation_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":401,"last_update":"2026-07-28T11:42:26.314877Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001584/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001584/DRAFT","etag":"935e60960cc4e27f3773c4d16cf7f6c66452b66bd9f97db83d5bec13fe71a498","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Function (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Function (UniProtKB) dataset contains biological function annotation for Bundibugyo virus [taxid:565995] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_function_uniprotkb.csv","filename":"bdbv_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_function_uniprotkb.stat.csv","filename":"bdbv_protein_function_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":329,"last_update":"2026-07-28T11:42:29.363309Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001585/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001585/DRAFT","etag":"8765eeeadcbf7dd710fa686f43ad2ae773323193f053aec9872e4de3dabac565","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Gene Symbols (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for Bundibugyo virus [taxid:565995] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_genenames_uniprotkb.csv","filename":"bdbv_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_genenames_uniprotkb.stat.csv","filename":"bdbv_protein_genenames_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":504,"last_update":"2026-07-28T11:42:32.409054Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001586/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001586/DRAFT","etag":"96ba49545e30349bb8c9fdba7776d8cb307f8ed355b9f616b78c946d7737d790","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) N-Glycosylation Sequon","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for Bundibugyo virus [taxid:565995] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_glycosylation_motifs.csv","filename":"bdbv_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_glycosylation_motifs.stat.csv","filename":"bdbv_protein_glycosylation_motifs.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":425,"last_update":"2026-07-28T11:42:35.457400Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001587/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001587/DRAFT","etag":"eabf45f3a8deda3cd577d6dc07241f2b7f6f03a5ac564063a7ec693250fce3b8","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Gene Ontology (GO)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Gene Ontology (GO) dataset contains Bundibugyo virus [taxid:565995] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_go_annotation.csv","filename":"bdbv_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_go_annotation.stat.csv","filename":"bdbv_protein_go_annotation.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":336,"last_update":"2026-07-28T11:42:38.506734Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001588/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001588/DRAFT","etag":"9bc118a1623145860d55d0ed7e3eb1dc4961ba8d2923d7db048af4046c0bcfaf","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) IEDB epitopes","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":"","created":"","modified":"","review":[],"contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Ebola (BDBV) epitope IEDB dataset contains Bundibugyo virus [taxid:565995] IEDB epitopes data from the UniProt Proteins Epitope REST API (www.ebi.ac.uk/proteins/api). If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB epitopes","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the epitope data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_iedb.csv","filename":"bdbv_protein_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_iedb.stat.csv","filename":"bdbv_protein_iedb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":527,"last_update":"2026-07-28T11:42:41.552894Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001589/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001589/DRAFT","etag":"83689bc870a8aa4649392d9d44b5af231eda6e535ffda5ecc27e808108b04379","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Information (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Information (NCBI RefSeq) dataset contains Bundibugyo virus [taxid:565995] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_info_refseq.csv","filename":"bdbv_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_info_refseq.stat.csv","filename":"bdbv_protein_info_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":365,"last_update":"2026-07-28T11:42:44.597285Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001590/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001590/DRAFT","etag":"36bb48148eb88ad9473f9551f1d0618bcaa3be2a55cb770ffc7cd329bf9a1ebb","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Information (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Information dataset contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_info_uniprotkb.csv","filename":"bdbv_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_info_uniprotkb.stat.csv","filename":"bdbv_protein_info_uniprotkb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2026-07-28T11:42:47.643970Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001591/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001591/DRAFT","etag":"b60ba4c09bfd09ce8e12936cd88280cdcef8d58142dddc6ff6c12ae21c8b7146","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Proteome Masterlist (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Proteome Masterlist dataset contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_masterlist.csv","filename":"bdbv_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_masterlist.stat.csv","filename":"bdbv_protein_masterlist.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":371,"last_update":"2026-07-28T11:42:50.689763Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001592/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001592/DRAFT","etag":"32897a6e4c52a594b99c574e94b60fbcc2edd418280b2d89f8056c8c7ea10003","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) EBI-UniProtKB NT file","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) EBI-UniProtKB NT file contains proteome data for Bundibugyo virus [taxid:565995] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tag"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","version":"","step_number":0,"input_list":[],"output_list":[],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"nt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_ntdata.nt","filename":"bdbv_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_ntdata.stat.csv","filename":"bdbv_protein_ntdata.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":344,"last_update":"2026-07-28T11:42:53.740564Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001593/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001593/DRAFT","etag":"65b992ee7a9fc40b52f3c6cb948159c8bda59cf1a277a8830be8a6a0428fdee8","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Names (NCBI RefSeq)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Names (NCBI RefSeq) dataset contains Bundibugyo virus [taxid:565995] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_proteinnames_refseq.csv","filename":"bdbv_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_proteinnames_refseq.stat.csv","filename":"bdbv_protein_proteinnames_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":332,"last_update":"2026-07-28T11:42:56.786978Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001594/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001594/DRAFT","etag":"8062f0eb1454101a02e711675f861d233c2ab7257d133ac743f4c885310fac25","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Recommended Names (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Recommended Names (UniProtKB) dataset contains Bundibugyo virus [taxid:565995]  UniProtKB recommended names for proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_recnames.csv","filename":"bdbv_protein_recnames.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_recnames.stat.csv","filename":"bdbv_protein_recnames.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":289,"last_update":"2026-07-28T11:42:59.832028Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001595/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001595/DRAFT","etag":"6bcc8b068b7cb6963f51563a039151f33af6e54bf7cb67f2d0835ccbb1514c4f","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Sequence Info (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Sequence Info (UniProtKB) dataset contains Bundibugyo virus [taxid:565995] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all bdbv isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_sequenceinfo.csv","filename":"bdbv_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_sequenceinfo.stat.csv","filename":"bdbv_protein_sequenceinfo.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":347,"last_update":"2026-07-28T11:43:02.880313Z","access_count":2},{"object_id":"https://biocomputeobject.org/GLY_001596/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001596/DRAFT","etag":"582cc206bf8ea4c4d4e4867ad21d57091582114dbcc9176db21c761636498409","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Site Annotation","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Site Annotation (UniProtKB) dataset contains Bundibugyo virus [taxid:565995] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_site_annotation_uniprotkb.csv","filename":"bdbv_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_site_annotation_uniprotkb.stat.csv","filename":"bdbv_protein_site_annotation_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":393,"last_update":"2026-07-28T11:43:05.928103Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001597/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001597/DRAFT","etag":"409edd475083087e6aae5ff8f367987853939ae7dc08557d11f044a73857d1d7","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref NCBI Gene","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) UniProtKB Xref NCBI Gene dataset contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_geneid.csv","filename":"bdbv_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_geneid.stat.csv","filename":"bdbv_protein_xref_geneid.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":625,"last_update":"2026-07-28T11:43:08.975317Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001598/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001598/DRAFT","etag":"60ddbaf93335cf8f0d1747761acdfd194113759e0f53f82569e314a169955ddf","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Xref iCn3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","contribution":["createdBy"],"email":"maria.kim@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Xref iCn3D dataset contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers in iCn3D. If you use this dataset please provide proper attribution to iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"iCn3D cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["3D structure","iCn3D","cross-reference"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_icn3d.csv","filename":"bdbv_protein_xref_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_icn3d.stat.csv","filename":"bdbv_protein_xref_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":537,"last_update":"2026-07-28T11:43:12.021767Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001599/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001599/DRAFT","etag":"812a23523ac8fb67a394983205ea431f854f6699e8bbe98133339950995d9c0d","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref IEDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","derived_from":"","created":"","modified":"","review":[],"contributors":[{"name":"Jeet Vora","orcid":"","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"},{"name":"Mariia Kim","affiliation":"The George Washington University","email":"maria.kim@gwu.edu","contribution":["createdBy"]}]},"usability_domain":["The Ebola (BDBV) UniProtKB Xref IEDB dataset contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to IEDB accessions/identifiers. If you use this dataset provide proper attribution to IEDB, GlyGen and EBI-EMBL-UniProtKB.","The Immune Epitope Database (IEDB) catalogs experimental data on antibody and T cell epitopes in the context of infectious disease, allergy, autoimmunity and transplantation."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"IEDB cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["Epitope","IEDB"],"xref":[],"platform":[],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IEDB database accessions/identifiers in the input file.","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_iedb.csv","filename":"bdbv_protein_xref_iedb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_iedb.stat.csv","filename":"bdbv_protein_xref_iedb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":521,"last_update":"2026-07-28T11:43:15.069769Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001600/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001600/DRAFT","etag":"74c89024075834735372eb850d474f2364bb34a489adb728fbc58fbeb6d0704b","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref InterPro","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) UniProtKB Xref InterPro contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_interpro.csv","filename":"bdbv_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_interpro.stat.csv","filename":"bdbv_protein_xref_interpro.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":576,"last_update":"2026-07-28T11:43:18.119457Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001601/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001601/DRAFT","etag":"65571f58ed848bfeaab34ce39e1081ff16bae98425ce910ed60310e636021da6","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) UniProtKB Xref PDB contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_pdb.csv","filename":"bdbv_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_pdb.stat.csv","filename":"bdbv_protein_xref_pdb.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":487,"last_update":"2026-07-28T11:43:21.169045Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001602/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001602/DRAFT","etag":"b08c814ff9ed78ac557cd87c076cf448f67810c1252d5d257828d735be7d3d7d","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) UniProtKB Xref extended PDB IDs contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to PDB database extended accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, GlyGen and PDB. ","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein 3D structure","PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PDB database accessions/identifiers from the triplestore containing triples from the nt file, reformats the IDs into the extended PDB ID format and extracts the data as a csv dataset.","prerequisite":[],"output_list":[]}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_pdb_extended.csv","filename":"bdbv_protein_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_pdb_extended.stat.csv","filename":"bdbv_protein_xref_pdb_extended.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":519,"last_update":"2026-07-28T11:43:24.218780Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001603/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001603/DRAFT","etag":"e0bc8d222ca57ed1a58635e148ae510b8635d61c62dab05fc3d03e04f46acd51","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref Pfam","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) UniProtKB Xref Pfam contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_pfam.csv","filename":"bdbv_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_pfam.stat.csv","filename":"bdbv_protein_xref_pfam.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":486,"last_update":"2026-07-28T11:43:27.266727Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001604/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001604/DRAFT","etag":"59a48b71c144411c61047fdff60515e2045ceec5a2cb3a5b11362d87e22eeda0","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref RefSeq","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) UniprotKB Xref RefSeq contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. "," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. "],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_refseq.csv","filename":"bdbv_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_refseq.stat.csv","filename":"bdbv_protein_xref_refseq.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":783,"last_update":"2026-07-28T11:43:30.315679Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001605/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001605/DRAFT","etag":"0fdb97508498c5a593030532acd89692c473b5628fa0f1bc65bb4c4699f3913a","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) UniProtKB Xref (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) UniProtKB Xref (UniProtKB) dataset contains Bundibugyo virus [taxid:565995] UniProtKB canonical accessions cross-referenced to UniProtKB  database accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniProtKB","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_uniprotkb.csv","filename":"bdbv_protein_xref_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_uniprotkb.stat.csv","filename":"bdbv_protein_xref_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":325,"last_update":"2026-07-28T11:43:33.365096Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001606/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001606/DRAFT","spec_version":"1.3.0","etag":"c312521befc8cde66fa4621a4cac1f0fae28216091bbca07c4b8b64496ee54d8","provenance_domain":{"name":"Ebola (BDBV) Predicted O-Glycosylation Sites (IsoGlyP)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-07-28T14:06:13.766Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Predicted O-Glycosylation Sites dataset contains predicted Bundibugyo virus (TaxID:565995) O-linked Glycosylation sites derived from the IsoGlyP tool and mapped to UniProtKB canonical accessions . This tool was developed by Jonathon E Mohl and colleagues and aims to identify position-specific enhancement values that are derived from GalNAc-T isoform-specific amino acid preferences in order to estimate the likelihood of a site being glycosylated by a specific transferase. Predicted sites included in the dataset were selected based on meeting a stringent EVP threshold score of 10 or higher (https://isoglyp.utep.edu/)."],"description_domain":{"pipeline_steps":[{"name":"tool_wrapper.py","step_number":1,"input_list":[],"description":"The script takes a path twords a canonical sequences fasta and runs it through the IsoGlyP O-Glycosylation prediction software. This process is slow so it is broken into 10 seperate processes."},{"name":"combine_csv.py","step_number":2,"input_list":[],"description":"The script takes the output of the previous step and combines them into one final dataset."}],"keywords":["O-Glycosylation","Predicted"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_predicted_isoglyp.csv","filename":"bdbv_proteoform_glycosylation_sites_predicted_isoglyp.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv","filename":"bdbv_proteoform_glycosylation_sites_predicted_isoglyp.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"filename":"tool_wrapper.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}},{"uri":{"filename":"combine_csv.py","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":773,"last_update":"2026-07-28T14:06:13.766415Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001607/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001607/DRAFT","spec_version":"1.3.0","etag":"6290bcb94b54281c8fba5689d3633e33d766ac2d21a6729f3dc0a8ac64b05cf6","provenance_domain":{"name":"Ebola (BDBV) Glycan Tissue Expression TableMaker","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-07-28T14:37:01.256Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"karinamartinez@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Dan Lyman","affiliation":"The George Washington University","contribution":["createdBy","curatedBy"],"email":"danlyman@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Glycan Tissue Expression TableMaker dataset provides glycan tissue expression annotations for Bundibugyo virus [TaxID: 565995]. Annotated by the TableMaker team, this dataset is available through GlyGen. More details can be found here: https://glygen.ccrc.uga.edu/tablemaker/."],"description_domain":{"pipeline_steps":[{"step_number":1,"input_list":[]}],"keywords":["TableMaker","glycan"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_tablemaker.csv","filename":"bdbv_proteoform_glycosylation_sites_tablemaker.csv"},"mediatype":"csv"},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_tablemaker.stat.csv","filename":"bdbv_proteoform_glycosylation_sites_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycan Tissue Expression TableMaker","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Bundibugyo virus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2026-07-28T14:37:01.256456Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001608/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001608/DRAFT","spec_version":"1.3.0","etag":"3b65e559ff9e67799c152bba6a53a9317801f57602047b881e3e2cec7a53047f","provenance_domain":{"name":"Ebola (BDBV) Glycosylation Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"affiliation":"The George Washington University","contribution":["createdBy"],"name":"Karina Martinez","email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Glycosylation Sites (UniProtKB) dataset contains Bundibugyo virus [TaxID:565995] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Bundibugyo virus proteome release."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_uniprotkb.csv","filename":"bdbv_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"bdbv_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":354,"last_update":"2026-07-28T11:43:42.513647Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001609/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001609/DRAFT","spec_version":"1.3.0","etag":"786356c2c30f5aabeadc8027b0ecca4c69b48b83dfeb2c92c52f32fc29ac4c48","provenance_domain":{"name":"Human Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-08-05T10:06:02.452Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Glycosylation Sites and Glycans view (iCn3D) dataset contains Homo sapiens [taxid:9606] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file."}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_icn3d.csv","filename":"human_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"human_proteoform_glycosylation_sites_icn3d.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1212,"last_update":"2026-08-05T10:06:02.452101Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001610/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001610/DRAFT","etag":"bd4af66ca8723eaeeb6f23ba8449f836b88c09fea36442021dfe8d43a229ee1b","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Glycosylation Sites and Glycans view (iCn3D) dataset contains Arabidopsis thaliana [taxid:3702] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_glycosylation_sites_icn3d.csv","filename":"arabidopsis_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"arabidopsis_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1229,"last_update":"2026-08-05T12:28:03.957369Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001611/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001611/DRAFT","etag":"5aa027805a2af50afd70fc1955fd8038dd96e26de12c0471f4d87f4622784ec6","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Glycosylation Sites and Glycans view (iCn3D) dataset contains Bos taurus [taxid:9913] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_icn3d.csv","filename":"bovine_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"bovine_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1211,"last_update":"2026-08-05T12:28:07.009566Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001612/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001612/DRAFT","etag":"41a979071ba79b089cccd3f2dee82dd105bc3e38ac64946d6449dad3ff313baa","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Glycosylation Sites and Glycans view (iCn3D) dataset contains Gallus gallus [taxid:9031] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_icn3d.csv","filename":"chicken_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"chicken_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1215,"last_update":"2026-08-05T12:28:10.062839Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001613/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001613/DRAFT","etag":"b91aacbb97d146dd7b75dae10f8e8a391d89b80813ed9511334d884e9cb41632","spec_version":"1.3.0","provenance_domain":{"name":"Dicty Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Glycosylation Sites and Glycans view (iCn3D) dataset contains Dictyostelium discoideum [taxid:44689] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycosylation_sites_icn3d.csv","filename":"dicty_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"dicty_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1227,"last_update":"2026-08-05T12:28:13.110866Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001614/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001614/DRAFT","etag":"0385386e2de6f41b43176fa03edec2690f1c6c76530a9609ec8950c2da024c8f","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Glycosylation Sites and Glycans view (iCn3D) dataset contains Drosophila melanogaster [taxid:7227] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_icn3d.csv","filename":"fruitfly_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"fruitfly_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1229,"last_update":"2026-08-05T12:28:16.161345Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001615/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001615/DRAFT","etag":"95ea64c31950d0755b26cf160123a90e21957e97cb129bba9db0fe4406a68ab1","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Glycosylation Sites and Glycans view (iCn3D) dataset contains Mus musculus [taxid:10090] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_icn3d.csv","filename":"mouse_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"mouse_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1213,"last_update":"2026-08-05T12:28:19.212825Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001616/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001616/DRAFT","etag":"89fded13244cb627741388e9f4c8be83c108884fb03b076025ad2a25bc51c042","spec_version":"1.3.0","provenance_domain":{"name":"Pig Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Glycosylation Sites and Glycans view (iCn3D) dataset contains Sus scrofa [taxid:1758] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_icn3d.csv","filename":"pig_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"pig_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1207,"last_update":"2026-08-05T12:28:22.260933Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001617/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001617/DRAFT","etag":"41d35d4edc7c640f3c7240f3cc55a6c479c86913ff5fd538462674f347e9c7d8","spec_version":"1.3.0","provenance_domain":{"name":"Rat Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Glycosylation Sites and Glycans view (iCn3D) dataset contains Rattus norvegicus [taxid:11106] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_icn3d.csv","filename":"rat_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"rat_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1217,"last_update":"2026-08-05T12:28:25.311962Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001618/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001618/DRAFT","etag":"a8854b478ae2f74349bf3b5fddb509a882c03d05c2eca2b0046a0702105db630","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV1 Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) Glycosylation Sites and Glycans view (iCn3D) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_proteoform_glycosylation_sites_icn3d.csv","filename":"sarscov1_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1292,"last_update":"2026-08-05T12:28:28.363456Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001619/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001619/DRAFT","etag":"05b643d68e5e2ed3ba505ee4b73aa74f8c6f5e703821936d8c485a7efa5ec655","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV2 Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Glycosylation Sites and Glycans view (iCn3D) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_icn3d.csv","filename":"sarscov2_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1302,"last_update":"2026-08-05T12:28:31.410202Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001620/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001620/DRAFT","etag":"7b3a68abaf3250519cbc328a385b2629e7740e9a7b48ebf72032ed48546d97ae","spec_version":"1.3.0","provenance_domain":{"name":"Yeast Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Glycosylation Sites and Glycans view (iCn3D) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_icn3d.csv","filename":"yeast_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"yeast_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1236,"last_update":"2026-08-05T12:28:34.460473Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001621/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001621/DRAFT","etag":"a3eb156f3b105300e4f8c5f01fea0fa7316c959cbc183df1834700a499f75f2d","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Glycosylation Sites and Glycans view (iCn3D) dataset contains Cricetulus griseus [TaxID:10029] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_icn3d.csv","filename":"hamster_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"hamster_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1223,"last_update":"2026-08-05T12:28:37.509683Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001622/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001622/DRAFT","etag":"1ce7ad6ac8ef39370b2c8adf1de6b9b8c7c70b137d3ec6d35fb935230fb1a309","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV-2 Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with SARS coronavirus (SARS-CoV-2 or 2019-nCoV) [TaxID: 2697049] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_lectin_unilectin3d.csv","filename":"sarscov2_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_lectin_unilectin3d.stat.csv","filename":"sarscov2_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":627,"last_update":"2026-08-18T13:32:45.529835Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001623/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001623/DRAFT","etag":"3724bcdb9f8fa2f0331d332623a8b001e63dfe27cf04854d5e3bbc25305a850a","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Arabidopsis thaliana [TaxID: 3702] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_lectin_unilectin3d.csv","filename":"arabidopsis_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_lectin_unilectin3d.stat.csv","filename":"arabidopsis_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":597,"last_update":"2026-08-18T13:35:53.673605Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001624/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001624/DRAFT","etag":"cb64c3b2079cfced8af14cb33bf76993f39805bf59959d2cc074c6ada296ebb5","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Bos taurus [TaxID: 9913] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_lectin_unilectin3d.csv","filename":"bovine_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_lectin_unilectin3d.stat.csv","filename":"bovine_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":585,"last_update":"2026-08-18T13:38:17.344222Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001625/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001625/DRAFT","etag":"b4c27171a15e6a0e39d98c28d668d4228612f4caf9441e54b1a720c3bc01cfe6","spec_version":"1.3.0","provenance_domain":{"name":"Pig Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Sus scrofa [TaxID: 9823] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_lectin_unilectin3d.csv","filename":"pig_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_lectin_unilectin3d.stat.csv","filename":"pig_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":585,"last_update":"2026-08-18T13:40:06.306908Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001626/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001626/DRAFT","etag":"c182dc87bc7cebab9c5e7e8504c51b98513a5eb322b34a29ac797ac50fab2f64","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Drosophila melanogaster [TaxID: 7227] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_lectin_unilectin3d.csv","filename":"fruitfly_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_lectin_unilectin3d.stat.csv","filename":"fruitfly_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":601,"last_update":"2026-08-18T13:42:05.091316Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001627/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001627/DRAFT","etag":"e3450e7a0ec261dad9a021b8fb3ed0299b74103956521a2a77bea56a34c9785c","spec_version":"1.3.0","provenance_domain":{"name":"Human Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Homo sapiens [TaxID: 9606] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_lectin_unilectin3d.csv","filename":"human_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_lectin_unilectin3d.stat.csv","filename":"human_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":588,"last_update":"2026-08-18T13:43:33.692166Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001628/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001628/DRAFT","etag":"e1f1e308f4c8eacca1f16616e7698ff67f6d1cc7cd114624654543cacffa1b02","spec_version":"1.3.0","provenance_domain":{"name":"Rat Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Rattus norvegicus [TaxID: 10116] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_lectin_unilectin3d.csv","filename":"rat_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_lectin_unilectin3d.stat.csv","filename":"rat_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":595,"last_update":"2026-08-18T13:45:15.124256Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001629/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001629/DRAFT","etag":"d9bc6b09aa3b18f85efe9943af8f3b66a1591e9ad2e8ec254601272124243b19","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Danio rerio [TaxID: 7955] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_lectin_unilectin3d.csv","filename":"zebrafish_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_lectin_unilectin3d.stat.csv","filename":"zebrafish_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":587,"last_update":"2026-08-18T13:47:01.580402Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001630/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001630/DRAFT","etag":"e5d4ffdb414386bfbf37eeaf3a2e500bce3004e0eed4b2e01299dc22d1df6baf","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Gallus gallus [TaxID: 9031] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_lectin_unilectin3d.csv","filename":"chicken_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_lectin_unilectin3d.stat.csv","filename":"chicken_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":589,"last_update":"2026-08-18T13:48:32.992823Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001631/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001631/DRAFT","etag":"738e33b858c189a68b13b890133c79ee1f50812580834036fb66e021eb96623f","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Mus musculus [TaxID: 10090] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_lectin_unilectin3d.csv","filename":"mouse_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_lectin_unilectin3d.stat.csv","filename":"mouse_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":589,"last_update":"2026-08-18T13:50:18.863432Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001632/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001632/DRAFT","etag":"529cca9a8c691557580389844c18fdfdc94800d8499f093cbdf3aa6dadd781a7","spec_version":"1.3.0","provenance_domain":{"name":"Yeast Lectin UniLectin3D","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Saccharomyces cerevisiae S288C [TaxID: 559292] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_lectin_unilectin3d.csv","filename":"yeast_protein_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_lectin_unilectin3d.stat.csv","filename":"yeast_protein_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":612,"last_update":"2026-08-18T13:52:27.685736Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001633/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001633/DRAFT","etag":"e5bb176b4966cce8c47e8090683a5bc1b8c15299e9cbc5a279ef22957cf070bc","spec_version":"1.3.0","provenance_domain":{"name":"Pig Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Sus scrofa [TaxID: 9823] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_lectin_unilectin3d.csv","filename":"pig_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_lectin_unilectin3d.stat.csv","filename":"pig_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":609,"last_update":"2026-08-18T13:57:07.683890Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001634/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001634/DRAFT","etag":"cc37c65d1c3d2c5e692952ed961b121a5d5a1c7441c54ff9cb06541bb3e867cf","spec_version":"1.3.0","provenance_domain":{"name":"Yeast Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Saccharomyces cerevisiae S288C [TaxID: 559292] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_lectin_unilectin3d.csv","filename":"yeast_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_lectin_unilectin3d.stat.csv","filename":"yeast_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":636,"last_update":"2026-08-18T13:58:39.401421Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001635/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001635/DRAFT","etag":"8b23cf0af105ee770ff2eaee87fca6679ac2a6f3f79d2e61b5d9f4e8df4ae900","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Bos taurus [TaxID: 9913] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_lectin_unilectin3d.csv","filename":"bovine_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_lectin_unilectin3d.stat.csv","filename":"bovine_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":609,"last_update":"2026-08-18T14:00:13.497668Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001636/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001636/DRAFT","etag":"9956df11134a2219e377a3deae197811a17b12ab79ca586c14b58b75f7b992fc","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Gallus gallus [TaxID: 9031] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_lectin_unilectin3d.csv","filename":"chicken_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_lectin_unilectin3d.stat.csv","filename":"chicken_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2026-08-18T14:03:01.581046Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001637/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001637/DRAFT","etag":"1d94caef248295675dc8d1e4be1356ea0e46e2de562c3c35993c17cb08183f75","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Drosophila melanogaster [TaxID: 7227] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_lectin_unilectin3d.csv","filename":"fruitfly_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_lectin_unilectin3d.stat.csv","filename":"fruitfly_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":625,"last_update":"2026-08-18T14:04:58.065468Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001638/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001638/DRAFT","etag":"457913831196904bd0c00430b2bec3e6fd390ee7312e96992b59fff91f0e4113","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV-2 Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2 or 2019-nCoV) [TaxID: 2697049] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_lectin_unilectin3d.csv","filename":"sarscov2_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_lectin_unilectin3d.stat.csv","filename":"sarscov2_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":689,"last_update":"2026-08-18T14:08:32.662736Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001639/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001639/DRAFT","etag":"f29da970da9f23a7486d09e86eb177fde72ee8854b0cf9f4bb3a64a21ce87076","spec_version":"1.3.0","provenance_domain":{"name":"Human Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Homo sapiens [TaxID: 9606] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_lectin_unilectin3d.csv","filename":"human_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_lectin_unilectin3d.stat.csv","filename":"human_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":612,"last_update":"2026-08-18T14:11:04.282220Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001640/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001640/DRAFT","etag":"ebded1a9f41d2d05774e2a6d22f3d605b09cfc0155b92eb2af0b87e0f5ae4bb1","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Mus musculus [TaxID: 10090] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_lectin_unilectin3d.csv","filename":"mouse_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_lectin_unilectin3d.stat.csv","filename":"mouse_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":613,"last_update":"2026-08-18T14:12:34.135974Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001641/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001641/DRAFT","etag":"e8cb05e7ec6671a5fb71f7a8b4371ec0660f41f77e4094461a1330dce5625f76","spec_version":"1.3.0","provenance_domain":{"name":"Rat Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Rattus norvegicus [TaxID: 10116] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_lectin_unilectin3d.csv","filename":"rat_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_lectin_unilectin3d.stat.csv","filename":"rat_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":619,"last_update":"2026-08-18T14:15:19.265356Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001642/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001642/DRAFT","etag":"cf62b23a476b5aef6129b2f2c0dc54506c489677428b71292aa754e384777281","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Arabidopsis thaliana [TaxID: 3702] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_lectin_unilectin3d.csv","filename":"arabidopsis_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_lectin_unilectin3d.stat.csv","filename":"arabidopsis_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":621,"last_update":"2026-08-18T14:26:53.668729Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001643/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001643/DRAFT","etag":"e94277093c6f6e4b6b9ed81ad8e4e33094dfa0827d361ae796ba6f4286d5d96e","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Lectin UniLectin3D Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains the citations provided as evidence for each lectin class associated with Danio rerio [TaxID: 7955] provided by UniLectin3D. UniLectin3D (https://unilectin.unige.ch/unilectin3D/) is a manually curated database of three-dimensional structures of carbohydrate-binding proteins, known as lectins. It classifies lectins by organism origin, protein fold, and binding family, providing structural details on interactions with glycan ligands as part of the broader UniLectin portal."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["UniLectin3D","Lectins","Citations"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_lectin_unilectin3d.csv","filename":"zebrafish_protein_citations_lectin_unilectin3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_lectin_unilectin3d.stat.csv","filename":"zebrafish_protein_citations_lectin_unilectin3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":611,"last_update":"2026-08-18T14:29:10.565759Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001644/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001644/DRAFT","etag":"cfec0c28eb5940cda7699e2f62673161a1edc4e38452601d6dd77daa36e512fa","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Xref GlyTableMaker","version":"v-x.x.xx","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:55:11.149043","modified":"2024-05-17T11:23:55.326Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides cross-references to GlyTableMaker entries for the associated glycans (GlyTouCan Accession) that were manually curated on GlyTableMaker (https://glygen.ccrc.uga.edu/tablemaker)"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyTableMaker cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Arabidopsis thaliana"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Danio rerio"},{"category_name":"species","category_value":"Dictyostelium discoideum"},{"category_name":"species","category_value":"Zaire ebolavirus (strain Mayinga-76)"},{"category_name":"species","category_value":"Bundibugyo virus"},{"category_name":"species","category_value":"Bos taurus"},{"category_name":"species","category_value":"Gallus gallus"},{"category_name":"species","category_value":"Cricetulus griseus"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyTableMaker","Cross-references"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_tablemaker.csv","filename":"glycan_xref_tablemaker.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_tablemaker.stat.csv","filename":"glycan_xref_tablemaker.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":241,"last_update":"2026-08-18T14:57:01.989993Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001645/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001645/DRAFT","spec_version":"1.3.0","etag":"451aafcca28d52913e362abc73179fc3f785fbdcd734070fe25b4bb981cc1085","provenance_domain":{"name":"Bundibugyo virus Xref GlyTableMaker","version":"v-x.x.xx","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:55:11.149043","modified":"2026-08-18T15:16:03.452Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides cross-references to GlyTableMaker entries for the proteins (UniProtKB Accessions) associated with Bundibugyo virus [TaxID: 565995] that were manually curated on GlyTableMaker (https://glygen.ccrc.uga.edu/tablemaker)"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the UniProtKB accessions based on the acession master list. Refer to the usability domain for more information on master list."}],"keywords":["Protein","UniProtKB Accession","GlyTableMaker","Cross-references"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_tablemaker.csv","filename":"bdbv_protein_xref_tablemaker.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_xref_tablemaker.stat.csv","filename":"bdbv_protein_xref_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyTableMaker cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Bundibugyo virus"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":289,"last_update":"2026-08-18T15:16:03.452333Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001646/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001646/DRAFT","spec_version":"1.3.0","etag":"2cc073b878b9074bf747c79a3aeb95df0bc1d4ed8c02355abb05ed84f81a2f08","provenance_domain":{"name":"Zaire ebolavirus (strain Mayinga-76) Xref GlyTableMaker","version":"v-x.x.xx","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:55:11.149043","modified":"2026-08-18T15:15:15.666Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides cross-references to GlyTableMaker entries for the proteins (UniProtKB Accessions) associated with Zaire ebolavirus (strain Mayinga-76) [TaxID: 128952] that were manually curated on GlyTableMaker (https://glygen.ccrc.uga.edu/tablemaker)"],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the UniProtKB accessions based on the acession master list. Refer to the usability domain for more information on master list."}],"keywords":["Protein","UniProtKB Accession","GlyTableMaker","Cross-references"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_tablemaker.csv","filename":"ebov_protein_xref_tablemaker.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_xref_tablemaker.stat.csv","filename":"ebov_protein_xref_tablemaker.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyTableMaker cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Zaire ebolavirus (strain Mayinga-76)"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":313,"last_update":"2026-08-18T15:15:15.666646Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001647/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001647/DRAFT","etag":"e557b18344dfdce2a00a7a20b607ebe4b5711d0062209097873bfd25efcb824c","spec_version":"1.3.0","provenance_domain":{"name":"Human Xref GlyTableMaker","version":"v-x.x.xx","license":"https://creativecommons.org/licenses/by/4.0/","created":"2019-11-13T16:55:11.149043","modified":"2024-05-17T11:23:55.326Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["This dataset provides cross-references to GlyTableMaker entries for the proteins (UniProtKB Accessions) associated with Homo sapiens [TaxID: 9606] that were manually curated on GlyTableMaker (https://glygen.ccrc.uga.edu/tablemaker)"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyTableMaker cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Homo sapiens"}]}}],"description_domain":{"keywords":["Protein","UniProtKB Accession","GlyTableMaker","Cross-references"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the UniProtKB accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_tablemaker.csv","filename":"human_protein_xref_tablemaker.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_xref_tablemaker.stat.csv","filename":"human_protein_xref_tablemaker.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":282,"last_update":"2026-08-18T15:14:14.098121Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001648/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001648/DRAFT","spec_version":"1.3.0","etag":"c8b0b9762a0c7cae605fd2e87dadbf2aa22824c1189da44fe388caf49b4caa5a","provenance_domain":{"name":"Human Lectin HumanLectome","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-08-18T15:51:16","modified":"2026-08-18T15:58:08.539Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains lectin class information for lectins associated with Homo sapiens [TaxID: 9606] provided by HumanLectome. HumanLectome is a specialized database and data module hosted on the UniLectin Portal that centralizes molecular, structural, and functional information on all known and predicted human lectins (carbohydrate-binding proteins)."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions."}],"keywords":["HumanLectome","Lectins"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_lectin_humanlectome.csv","filename":"human_protein_lectin_humanlectome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_lectin_humanlectome.stat.csv","filename":"human_protein_lectin_humanlectome.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":440,"last_update":"2026-08-18T15:58:08.539091Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001649/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001649/DRAFT","spec_version":"1.3.0","etag":"e7dc3278d1c6145cea149aa47ae5b80dc58d58971848a063a0cb53ac924f0de6","provenance_domain":{"name":"Human Lectin HumanLectome Citations","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"2026-08-18T15:51:16","modified":"2025-10-20T14:18:06.520Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The following dataset contains citation information for each lectin class for lectins associated with Homo sapiens [TaxID: 9606] provided by HumanLectome. HumanLectome is a specialized database and data module hosted on the UniLectin Portal that centralizes molecular, structural, and functional information on all known and predicted human lectins (carbohydrate-binding proteins)."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PDB IDs from the input .tsv files and maps it to the corresponding UniProtKB accessions.","prerequisite":[],"output_list":[]}],"keywords":["HumanLectome","Lectins","Citations"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_lectin_humanlectome.csv","filename":"human_protein_citations_lectin_humanlectome.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_lectin_humanlectome.stat.csv","filename":"human_protein_citations_lectin_humanlectome.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"UniLectin3D","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"sbhuiyan28","authorized_users":null,"state":"DRAFT","score":462,"last_update":"2026-08-18T15:59:53.203482Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001650/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001650/DRAFT","etag":"588005934a6e7ae54cb70f3cbdd206243ce9d05508e509eb75cb574df3583d8c","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis binding sites (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_binding_sites_uniprotkb.csv","filename":"arabidopsis_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_binding_sites_uniprotkb.stat.csv","filename":"arabidopsis_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":469,"last_update":"2026-08-18T20:56:44.091002Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001651/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001651/DRAFT","etag":"d3dabf359cef83809398010f665be7a963173c12638552ebdb20f7ad564526bb","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis binding sites citations (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_binding_sites_uniprotkb.csv","filename":"arabidopsis_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"arabidopsis_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2026-08-18T20:56:47.143966Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001652/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001652/DRAFT","etag":"3b719f8c898322c0656587221f78045a2c39986b934b7976246c812845e62a7b","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Protein Isoform sequences (UniProtKB) dataset contains Bundibugyo virus [taxid:565995] protein fasta sequences for the bdbv isoform accessions from the UniProtKB database,. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all bdbv isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_allsequences.fasta","filename":"bdbv_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_allsequences.stat.csv","filename":"bdbv_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":341,"last_update":"2026-08-18T20:56:50.199845Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001653/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001653/DRAFT","etag":"34b7e8aa1bbad0845554b998aa9ada19ffe3c22ac08b09f23d0880374ad3d58c","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine binding sites (UniProtKB) dataset contains Bos taurus [taxid:9913] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_binding_sites_uniprotkb.csv","filename":"bovine_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_binding_sites_uniprotkb.stat.csv","filename":"bovine_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":451,"last_update":"2026-08-18T20:56:53.258588Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001654/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001654/DRAFT","etag":"fdb110d0609ada71259820119f04a414b8d036badaac33922b2d7c17785e3781","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine binding sites citations (UniProtKB) dataset contains Bos taurus [taxid:9913] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_binding_sites_uniprotkb.csv","filename":"bovine_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"bovine_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":403,"last_update":"2026-08-18T20:56:56.312459Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001655/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001655/DRAFT","etag":"63419bbff774a8612665f0812e851198f9df26d3a8e9d6facfb827b7261dde64","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken binding sites (UniProtKB) dataset contains Gallus gallus [taxid:9031] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_binding_sites_uniprotkb.csv","filename":"chicken_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_binding_sites_uniprotkb.stat.csv","filename":"chicken_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":456,"last_update":"2026-08-18T20:56:59.364909Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001656/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001656/DRAFT","etag":"6e3e5658a306cd3ca8aaa8db14f13eb3b73f341a3c895f83852558dc0662cb64","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken binding sites citations (UniProtKB) dataset contains Gallus gallus [taxid:9031] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_binding_sites_uniprotkb.csv","filename":"chicken_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"chicken_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":408,"last_update":"2026-08-18T20:57:02.419202Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001657/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001657/DRAFT","etag":"972131d176f0ee444de1981c6b3e5ea87ea51a8805c63eb9ed00c0c9b947d890","spec_version":"1.3.0","provenance_domain":{"name":"Dicty Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty binding sites (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_binding_sites_uniprotkb.csv","filename":"dicty_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_binding_sites_uniprotkb.stat.csv","filename":"dicty_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":468,"last_update":"2026-08-18T20:57:05.471956Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001658/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001658/DRAFT","etag":"165451d383353d2f3085e3d0371416b6d783df79ae7e0c1640de400bd0a9ccba","spec_version":"1.3.0","provenance_domain":{"name":"Dicty Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty binding sites citations (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_binding_sites_uniprotkb.csv","filename":"dicty_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"dicty_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":420,"last_update":"2026-08-18T20:57:08.527990Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001659/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001659/DRAFT","etag":"04d740e4c30b23d52acc9bba57fc0180cfd082262ed1616bf918ad12ebda0996","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Protein Isoform sequences (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Maria Martin","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"martin@ebi.ac.uk"},{"name":"Preethi Vasudev","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"email":"pvasudev@ebi.ac.uk"},{"name":"Karina Martinez","affiliation":"The George Washington University","contribution":["createdBy"],"email":"karinamartinez@gwu.edu"},{"name":"Luke Johnson","affiliation":"The George Washington University","contribution":["createdBy"],"email":"luke.johnson@email.gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Cyrus Au-Yeung","affiliation":"The George Washington University","contribution":["createdBy"],"email":"cyruschauyeung@gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) Protein Isoform sequences (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] protein fasta sequences for the ebov isoform accessions from the UniProtKB database,. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tag"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all ebov isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"fasta","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_allsequences.fasta","filename":"ebov_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_allsequences.stat.csv","filename":"ebov_protein_allsequences.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":365,"last_update":"2026-08-18T20:57:11.586846Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001660/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001660/DRAFT","etag":"bca2fd48e972f31fe632ccedb7ae51626a2c921130129cdf03bc9b8364653f9f","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) binding sites (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_binding_sites_uniprotkb.csv","filename":"ebov_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_binding_sites_uniprotkb.stat.csv","filename":"ebov_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":492,"last_update":"2026-08-18T20:57:14.642176Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001661/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001661/DRAFT","etag":"66dfc094da5ead908d019b55936ca8b87895580df07b9556f43c4ff1d8a9269a","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) binding sites citations (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_binding_sites_uniprotkb.csv","filename":"ebov_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"ebov_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":444,"last_update":"2026-08-18T20:57:17.694566Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001662/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001662/DRAFT","etag":"d6827cdb79fc52f974d2cab5bc71e5c08d082012dc8402c878358f325fe33e67","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly binding sites (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_binding_sites_uniprotkb.csv","filename":"fruitfly_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_binding_sites_uniprotkb.stat.csv","filename":"fruitfly_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":469,"last_update":"2026-08-18T20:57:20.745844Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001663/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001663/DRAFT","etag":"f8fb175c0a0b49a246e27af0e14cbd636d4f35e63ef8111e1e67ab57a9bada35","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly binding sites citations (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_binding_sites_uniprotkb.csv","filename":"fruitfly_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"fruitfly_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":421,"last_update":"2026-08-18T20:57:23.801620Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001664/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001664/DRAFT","etag":"34e5098aeebdb7a2a51b32b2b9e0db8309f8ab5628f5a7b3974c4fa5a8a37d6d","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster binding sites (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_binding_sites_uniprotkb.csv","filename":"hamster_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_binding_sites_uniprotkb.stat.csv","filename":"hamster_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":463,"last_update":"2026-08-18T20:57:26.852454Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001665/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001665/DRAFT","etag":"e980ab2a670cd4b2e51935e9bde4e2f38f0677ae81f2f29c4bef91b608e035c2","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster binding sites citations (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_binding_sites_uniprotkb.csv","filename":"hamster_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"hamster_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":415,"last_update":"2026-08-18T20:57:29.906285Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001666/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001666/DRAFT","etag":"2e460427ccd4107aa2d8d2e4d324a8e1d8999966afa9593036d3e4eda3671eb2","spec_version":"1.3.0","provenance_domain":{"name":"HCV1a Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1a binding sites (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_binding_sites_uniprotkb.csv","filename":"hcv1a_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_binding_sites_uniprotkb.stat.csv","filename":"hcv1a_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":476,"last_update":"2026-08-18T20:57:32.960508Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001667/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001667/DRAFT","etag":"5da99caf37b63b78ee1f10fd3b4ea502b475a042a68b3d8a3eca1470a28a37cd","spec_version":"1.3.0","provenance_domain":{"name":"HCV1a Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1a binding sites citations (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_citations_binding_sites_uniprotkb.csv","filename":"hcv1a_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"hcv1a_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":428,"last_update":"2026-08-18T20:57:36.013373Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001668/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001668/DRAFT","etag":"c6b0a2321155b34f685be17c597a046207facb75397f7b0226874220f7507951","spec_version":"1.3.0","provenance_domain":{"name":"HCV1b Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1b binding sites (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_binding_sites_uniprotkb.csv","filename":"hcv1b_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_binding_sites_uniprotkb.stat.csv","filename":"hcv1b_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":482,"last_update":"2026-08-18T20:57:39.064957Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001669/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001669/DRAFT","etag":"51eb8bf7b712674b85ef0f72d7a9d52307b04c9ba2ad3dc7bbead296209750a9","spec_version":"1.3.0","provenance_domain":{"name":"HCV1b Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1b binding sites Citations (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_citations_binding_sites_uniprotkb.csv","filename":"hcv1b_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"hcv1b_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":434,"last_update":"2026-08-18T20:57:42.115524Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001670/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001670/DRAFT","etag":"62b1fe6146b4e0822efa744c4cc9a0d39d4f2809c60387e649b56f68a281841a","spec_version":"1.3.0","provenance_domain":{"name":"Human Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human binding sites (UniProtKB) dataset contains Homo sapiens [taxid:9606] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_binding_sites_uniprotkb.csv","filename":"human_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_binding_sites_uniprotkb.stat.csv","filename":"human_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":452,"last_update":"2026-08-18T20:57:45.167848Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001671/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001671/DRAFT","etag":"5053fcf863bebf9e9e69bb60c1b937633857ea40144295294f05195d5608e909","spec_version":"1.3.0","provenance_domain":{"name":"Human Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human binding sites citations (UniProtKB) dataset contains Homo sapiens [taxid:9606] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_binding_sites_uniprotkb.csv","filename":"human_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"human_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":404,"last_update":"2026-08-18T20:57:48.216347Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001672/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001672/DRAFT","etag":"5fb094fc23e602f1441ae0f1bbd657567e1fbe173cf62e08029ff8f82be47d7a","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse binding sites (UniProtKB) dataset contains Mus musculus [taxid:10090] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_binding_sites_uniprotkb.csv","filename":"mouse_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_binding_sites_uniprotkb.stat.csv","filename":"mouse_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":453,"last_update":"2026-08-18T20:57:51.264006Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001673/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001673/DRAFT","etag":"7b88bbf0fc5715f77d09cd6ba3aef16485fea3742fbc4d320584e99544120e80","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse binding sites citations (UniProtKB) dataset contains Mus musculus [taxid:10090] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_binding_sites_uniprotkb.csv","filename":"mouse_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"mouse_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":405,"last_update":"2026-08-18T20:57:54.317438Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001674/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001674/DRAFT","etag":"1807ad29c9a01c80d7ecea5b7c5d774b549cab37e7971ee18634f439d043bd3a","spec_version":"1.3.0","provenance_domain":{"name":"Pig Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig binding sites (UniProtKB) dataset contains Sus scrofa [taxid:9823] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_binding_sites_uniprotkb.csv","filename":"pig_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_binding_sites_uniprotkb.stat.csv","filename":"pig_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":447,"last_update":"2026-08-18T20:57:57.369737Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001675/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001675/DRAFT","etag":"f277d89b12d9f1b31e569574532ed99c43921b7e0fe2ec58cbc9932244bb87fa","spec_version":"1.3.0","provenance_domain":{"name":"Pig Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig binding sites citations (UniProtKB) dataset contains Sus scrofa [taxid:9823] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_binding_sites_uniprotkb.csv","filename":"pig_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"pig_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":399,"last_update":"2026-08-18T20:58:00.423259Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001676/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001676/DRAFT","etag":"2652cf8e058e0745860b0b20c5cb2655fc2519492e62c366efa6dad92fdeb019","spec_version":"1.3.0","provenance_domain":{"name":"Rat Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat binding sites (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_binding_sites_uniprotkb.csv","filename":"rat_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_binding_sites_uniprotkb.stat.csv","filename":"rat_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":457,"last_update":"2026-08-18T20:58:03.474192Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001677/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001677/DRAFT","etag":"0369e5612f2b03b4b46923b48785df4b306ba4949177a4b8a434564570b75b9d","spec_version":"1.3.0","provenance_domain":{"name":"Rat Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat binding sites citations (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_binding_sites_uniprotkb.csv","filename":"rat_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"rat_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":409,"last_update":"2026-08-18T20:58:06.524252Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001678/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001678/DRAFT","etag":"238ee558804be3ddad422ba94994cb7c2bed3a0b525b1611dabada98b871e30f","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV1 Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) binding sites (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_binding_sites_uniprotkb.csv","filename":"sarscov1_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_binding_sites_uniprotkb.stat.csv","filename":"sarscov1_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":533,"last_update":"2026-08-18T20:58:09.579383Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001679/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001679/DRAFT","etag":"a6772d392b73d50ec48d609f6c6db620146c18c7952cd440b8fdcac49bd3fa76","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV1 Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS-CoV1 binding sites citations (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_citations_binding_sites_uniprotkb.csv","filename":"sarscov1_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"sarscov1_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":461,"last_update":"2026-08-18T20:58:12.632295Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001680/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001680/DRAFT","etag":"3e005d1cf548fc2f811f991fc0dcb4b4f9da0efeb0889c6f4320993e2eefff5d","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV2 Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) binding sites (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_binding_sites_uniprotkb.csv","filename":"sarscov2_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_binding_sites_uniprotkb.stat.csv","filename":"sarscov2_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":542,"last_update":"2026-08-18T20:58:15.683936Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001681/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001681/DRAFT","spec_version":"1.3.0","etag":"728cdbf460f56c207cfdd3dce9793038950f5ba0d7e5df859df81c64ee1696df","provenance_domain":{"name":"SARS-CoV2 Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-08-18T21:04:47.980Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) binding sites citations (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB."}],"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_binding_sites_uniprotkb.csv","filename":"sarscov2_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"sarscov2_protein_citations_binding_sites_uniprotkb.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":494,"last_update":"2026-08-18T21:04:47.980091Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001682/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001682/DRAFT","etag":"e674a509a4bac4feecdce2f165a81507aa2f68c1f961a47d0dee4042a5970892","spec_version":"1.3.0","provenance_domain":{"name":"Yeast Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast binding sites (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_binding_sites_uniprotkb.csv","filename":"yeast_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_binding_sites_uniprotkb.stat.csv","filename":"yeast_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":476,"last_update":"2026-08-18T20:58:21.784556Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001683/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001683/DRAFT","etag":"358273f9e58fd68737e8957378ed1829aa1d8d49b2ff52e99444487f9fb84981","spec_version":"1.3.0","provenance_domain":{"name":"Yeast Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast binding sites citations (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_binding_sites_uniprotkb.csv","filename":"yeast_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"yeast_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":428,"last_update":"2026-08-18T20:58:24.837292Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001684/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001684/DRAFT","etag":"8a8835811f8957f021e6953c834fae3d92b5b327c6b6b7656977c96ee499670b","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Binding Sites (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish binding sites (UniProtKB) dataset contains Danio rerio [taxid:7955] interaction data between UniProtKB canonical protein binding sites and their interacting chemical entity. The physiological ligand is described by it's identifier in the ChEBI ontology, and the UniProt name. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the binding site position, ligand info and annotation comments from the Binding_Site_Annotation triples in the triplestore, maps the data to the UniProtKB canonical sequences, then uses the extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_binding_sites_uniprotkb.csv","filename":"zebrafish_protein_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_binding_sites_uniprotkb.stat.csv","filename":"zebrafish_protein_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":456,"last_update":"2026-08-18T20:58:27.887799Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001685/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001685/DRAFT","etag":"fe48c7014c5409aec2a424cd1ea4ffb36ae957181c36bb81c2ddf85c686d854f","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Binding Sites Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish binding sites citations (UniProtKB) dataset contains Danio rerio [taxid:7955] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binding sites citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["binding sites","ligands","metal binding sites","calcium binding sites","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_binding_sites_uniprotkb.csv","filename":"zebrafish_protein_citations_binding_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_binding_sites_uniprotkb.stat.csv","filename":"zebrafish_protein_citations_binding_sites_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":408,"last_update":"2026-08-18T20:58:30.942823Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001686/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001686/DRAFT","etag":"0085046218d07d50d2df7641205af2dc9fea973a2654753a68b91293a7344981","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Glycosylation Sites and Glycans view (iCn3D)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Glycosylation Sites and Glycans view (iCn3D) dataset contains Danio rerio [taxid:7955] proteins glycosites and attached glycans extracted from the RCSB PDB database using their search, data and sequence coordinates API (see GLY_001412). The generated PDB proteoform dataset is used to map the UniProtKB AC and residue position in our proteoform datasets to the PDB ID, author amino acid chain and author glycosylation site residue position, and construct the links to iCn3D (https://www.ncbi.nlm.nih.gov/Structure/icn3d/?bcifid=(PDB_ID)&bu=0&command=select .(amino_acid_chain_auth:glycosylation_site_auth);+center+selection;+zoom+selection) where you can view the highlighted glycosylation site within the 3D structure. If you use this dataset please provide proper attribution to PDB, iCn3D and GlyGen.","The I see in 3D (iCn3D) Structure Viewer is an interactive web-based structure analysis tool which synchronizes the display of 3D structures, 2D interactions, and 1D sequences and annotations."],"extension_domain":[{"dataset_extension":{"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"}],"description_domain":{"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the UniProtKB ACs, UniProtKB residues, PDB IDs, PDB and auth chain IDs, and PDB and auth glycosite information from the input .csv file.","prerequisite":[],"output_list":[]}],"keywords":["glycosylation","reported glycosylation","UniProtKB","PubMed","PDB","3D Structure","Data view","iCn3D"]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_icn3d.csv","filename":"zebrafish_proteoform_glycosylation_sites_icn3d.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_proteoform_glycosylation_sites_icn3d.stat.csv","filename":"zebrafish_proteoform_glycosylation_sites_icn3d.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1215,"last_update":"2026-08-18T20:58:33.995167Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001687/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001687/DRAFT","etag":"47a1bf7d6469b5c83ccf5b17e4ee44579382a5414c2af2e45a38e3fbd9f5a47f","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis domain and regions citations (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_domains_uniprotkb.csv","filename":"arabidopsis_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_citations_domains_uniprotkb.stat.csv","filename":"arabidopsis_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":450,"last_update":"2026-08-18T20:58:56.289851Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001688/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001688/DRAFT","etag":"90006c3e02313c60dfb62fae406c106a162db1e6a7eaabb3a54e2581b7216a01","spec_version":"1.3.0","provenance_domain":{"name":"Arabidopsis Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis domain and regions (UniProtKB) dataset contains Arabidopsis thaliana [taxid:3702] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_domains_uniprotkb.csv","filename":"arabidopsis_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_domains_uniprotkb.stat.csv","filename":"arabidopsis_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":374,"last_update":"2026-08-18T20:58:59.341402Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001689/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001689/DRAFT","etag":"858bf4d59e5f5484576e51db54d2d5d4876c3c5f6f21223c858cf979b969f185","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (BDBV) Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (BDBV) Domain and regions (UniProtKB) dataset contains Bundibugyo virus [taxid:565995] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bundibugyo virus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_domains_uniprotkb.csv","filename":"bdbv_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bdbv_protein_domains_uniprotkb.stat.csv","filename":"bdbv_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":373,"last_update":"2026-08-18T20:59:02.398233Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001690/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001690/DRAFT","etag":"41e2b96e8bb0bdf995a1c3788faeecced55e6c6751201c8f948d2eddf1650a09","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine domain and regions citations (UniProtKB) dataset contains Bos taurus [taxid:9913] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_domains_uniprotkb.csv","filename":"bovine_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_citations_domains_uniprotkb.stat.csv","filename":"bovine_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":432,"last_update":"2026-08-18T20:59:05.458263Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001691/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001691/DRAFT","etag":"5dd76475d910ee7cd625f5eb569dd5b5f41ba3ba89a0630d305f68578780fde0","spec_version":"1.3.0","provenance_domain":{"name":"Bovine Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine domain and regions (UniProtKB) dataset contains Bos taurus [taxid:9913] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_domains_uniprotkb.csv","filename":"bovine_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_domains_uniprotkb.stat.csv","filename":"bovine_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":356,"last_update":"2026-08-18T20:59:08.511886Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001692/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001692/DRAFT","etag":"5b0ea7ad06e8c2c27da2a730aa89a8fa9a91ab7dbc3c533f271ffd55c0364457","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken domain and regions citations (UniProtKB) dataset contains Gallus gallus [taxid:9031] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_domains_uniprotkb.csv","filename":"chicken_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_citations_domains_uniprotkb.stat.csv","filename":"chicken_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":437,"last_update":"2026-08-18T20:59:11.566713Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001693/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001693/DRAFT","etag":"9b2362d1c1ff144b70ae4deb027bbe284e9efbc38cd25b38e031944d933d8062","spec_version":"1.3.0","provenance_domain":{"name":"Chicken Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken domain and regions (UniProtKB) dataset contains Gallus gallus [taxid:9031] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_domains_uniprotkb.csv","filename":"chicken_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_domains_uniprotkb.stat.csv","filename":"chicken_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2026-08-18T20:59:14.620993Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001694/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001694/DRAFT","etag":"c7608498755ec5ef6f70bdd4ddb0db80cd3ede4a486c172616413634e9a44860","spec_version":"1.3.0","provenance_domain":{"name":"Dicty Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty domain and regions citations (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_domains_uniprotkb.csv","filename":"dicty_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_citations_domains_uniprotkb.stat.csv","filename":"dicty_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":449,"last_update":"2026-08-18T20:59:17.671199Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001695/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001695/DRAFT","etag":"5890d74fb6249db32f8d200f66d1f7aee18f2a24694ec2b8b27336a23b953163","spec_version":"1.3.0","provenance_domain":{"name":"Dicty Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty domain and regions (UniProtKB) dataset contains Dictyostelium discoideum [taxid:44689] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_domains_uniprotkb.csv","filename":"dicty_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_domains_uniprotkb.stat.csv","filename":"dicty_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":373,"last_update":"2026-08-18T20:59:20.721053Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001696/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001696/DRAFT","etag":"b889f74952839d0c3d45fff18f22da98e68be6bf6eea0b96708bf9a459e6ed81","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) domain and regions citations (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_domains_uniprotkb.csv","filename":"ebov_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_citations_domains_uniprotkb.stat.csv","filename":"ebov_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":473,"last_update":"2026-08-18T20:59:23.771792Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001697/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001697/DRAFT","etag":"189abdd41b06226e1dd39e1caebbaef90a01ac8414c7b6456d900b7c35d3feac","spec_version":"1.3.0","provenance_domain":{"name":"Ebola (EBOV) Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Ebola (EBOV) domain and regions (UniProtKB) dataset contains Zaire ebolavirus (strain Mayinga-76) [taxid:128952] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Zaire ebolavirus (strain Mayinga-76)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_domains_uniprotkb.csv","filename":"ebov_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/ebov_protein_domains_uniprotkb.stat.csv","filename":"ebov_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":397,"last_update":"2026-08-18T20:59:26.821911Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001698/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001698/DRAFT","etag":"c0c3d06a78e80f4b325f9a74d0dec10f01b33534fc4c255b499eb770ccbd2432","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly domain and regions citations (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_domains_uniprotkb.csv","filename":"fruitfly_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_domains_uniprotkb.stat.csv","filename":"fruitfly_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":450,"last_update":"2026-08-18T20:59:29.875198Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001699/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001699/DRAFT","etag":"c19640975b2563648f6f78f306eb5bbf12286917a860b0a9f5bb5fbc147074c6","spec_version":"1.3.0","provenance_domain":{"name":"Fruitfly Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly domain and regions (UniProtKB) dataset contains Drosophila melanogaster [taxid:7227] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_domains_uniprotkb.csv","filename":"fruitfly_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_domains_uniprotkb.stat.csv","filename":"fruitfly_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":374,"last_update":"2026-08-18T20:59:32.928233Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001700/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001700/DRAFT","etag":"6d41543088dd6c8823d1c80b644c0f372e0317c255828480f844f0c09318d466","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster domain and regions citations (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_domains_uniprotkb.csv","filename":"hamster_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_citations_domains_uniprotkb.stat.csv","filename":"hamster_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":444,"last_update":"2026-08-18T20:59:35.980482Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001701/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001701/DRAFT","etag":"cf327f0834b6e85c22b006e8be8421d41372a67551ff2dc0025a2b62e6b41ddb","spec_version":"1.3.0","provenance_domain":{"name":"Hamster Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster domain and regions (UniProtKB) dataset contains Cricetulus griseus [taxid:10029] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_domains_uniprotkb.csv","filename":"hamster_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_domains_uniprotkb.stat.csv","filename":"hamster_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":368,"last_update":"2026-08-18T20:59:39.031825Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001702/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001702/DRAFT","etag":"26fa1a8ae0a02362cd825625c9e9f9acfd6cc709ba3466dbd045ddb9e9c10cde","spec_version":"1.3.0","provenance_domain":{"name":"HCV1a Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1a domain and regions (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_domains_uniprotkb.csv","filename":"hcv1a_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_domains_uniprotkb.stat.csv","filename":"hcv1a_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":381,"last_update":"2026-08-18T20:59:42.081850Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001703/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001703/DRAFT","etag":"588025c5112bdb0a12044c1b73989b1156cd45364b223c1375870028bbc0c1b8","spec_version":"1.3.0","provenance_domain":{"name":"HCV1b Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1b domain and regions citations (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_citations_domains_uniprotkb.csv","filename":"hcv1b_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_citations_domains_uniprotkb.stat.csv","filename":"hcv1b_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":463,"last_update":"2026-08-18T20:59:45.132972Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001704/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001704/DRAFT","etag":"9fa2ff1ac7d05413af24a8a7ecb89e56c5b9f575f135df3736d7e3b919e3407f","spec_version":"1.3.0","provenance_domain":{"name":"HCV1b Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The HCV1b domain and regions (UniProtKB) dataset contains Hepatitis C virus (isolate Japanese) [taxid:11116] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Hepatitis C virus (isolate H77)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_domains_uniprotkb.csv","filename":"hcv1b_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1b_protein_domains_uniprotkb.stat.csv","filename":"hcv1b_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":387,"last_update":"2026-08-18T20:59:48.185981Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001705/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001705/DRAFT","etag":"cc158ca5decf70b35278f6481d9f30a6e0190a6b71650834ad205a36a8614310","spec_version":"1.3.0","provenance_domain":{"name":"Human Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human domain and regions citations (UniProtKB) dataset contains Homo sapiens [taxid:9606] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_domains_uniprotkb.csv","filename":"human_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_citations_domains_uniprotkb.stat.csv","filename":"human_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":433,"last_update":"2026-08-18T20:59:51.239577Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001706/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001706/DRAFT","etag":"c4f6cfb457cbdaeb4a724ad958252b507781ae331f6f72736f9642755993ef78","spec_version":"1.3.0","provenance_domain":{"name":"Human Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human domain and regions (UniProtKB) dataset contains Homo sapiens [taxid:9606] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_domains_uniprotkb.csv","filename":"human_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_domains_uniprotkb.stat.csv","filename":"human_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":357,"last_update":"2026-08-18T20:59:54.290014Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001707/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001707/DRAFT","etag":"ef37d3874638a66c69bc60efb2d44c0678bf17073a1e18fa910050851f59dfac","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse domain and regions citations (UniProtKB) dataset contains Mus musculus [taxid:10090] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_domains_uniprotkb.csv","filename":"mouse_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_citations_domains_uniprotkb.stat.csv","filename":"mouse_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":434,"last_update":"2026-08-18T20:59:57.338782Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001708/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001708/DRAFT","etag":"7a4ced87758c5f702b1a0c8baa5adffc0fd155a0aac1ec1098117299f4a1a1c6","spec_version":"1.3.0","provenance_domain":{"name":"Mouse Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse domain and regions (UniProtKB) dataset contains Mus musculus [taxid:10090] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_domains_uniprotkb.csv","filename":"mouse_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_domains_uniprotkb.stat.csv","filename":"mouse_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":359,"last_update":"2026-08-18T21:00:00.388150Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001709/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001709/DRAFT","etag":"6c75cc2b1fcd45177930cd88f7d395119447599f493940221c6b9d49eaec2f40","spec_version":"1.3.0","provenance_domain":{"name":"Pig Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig domain and regions citations (UniProtKB) dataset contains Sus scrofa [taxid:9823] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_domains_uniprotkb.csv","filename":"pig_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_citations_domains_uniprotkb.stat.csv","filename":"pig_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":428,"last_update":"2026-08-18T21:00:03.438620Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001710/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001710/DRAFT","etag":"fab71f1e4df94e9baf774c8527c28e0d62945b21f30abec238172a013e450959","spec_version":"1.3.0","provenance_domain":{"name":"Pig Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig domain and regions (UniProtKB) dataset contains Sus scrofa [taxid:9823] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_domains_uniprotkb.csv","filename":"pig_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_domains_uniprotkb.stat.csv","filename":"pig_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":353,"last_update":"2026-08-18T21:00:06.491561Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001711/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001711/DRAFT","etag":"9385a72ebf53da6771c56d2ae90780fb4e0c766400866615c8a5aa6f7f7e2aa9","spec_version":"1.3.0","provenance_domain":{"name":"Rat Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat domain and regions citations (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_domains_uniprotkb.csv","filename":"rat_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_citations_domains_uniprotkb.stat.csv","filename":"rat_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":438,"last_update":"2026-08-18T21:00:09.542064Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001712/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001712/DRAFT","etag":"ed5502c0b9a9df1084b829e8d6b14993eba62c87eb86594600a1aa70859b43ff","spec_version":"1.3.0","provenance_domain":{"name":"Rat Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat domain and regions (UniProtKB) dataset contains Rattus norvegicus [taxid:10116] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_domains_uniprotkb.csv","filename":"rat_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_domains_uniprotkb.stat.csv","filename":"rat_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":362,"last_update":"2026-08-18T21:00:12.593733Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001713/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001713/DRAFT","etag":"4ba2feb0ba60baf5906b8e6a38317a7b5d41dd93f75e2c442013ea3d24e779cc","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV1 Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) domain and regions citations (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_citations_domains_uniprotkb.csv","filename":"sarscov1_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_citations_domains_uniprotkb.stat.csv","filename":"sarscov1_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":513,"last_update":"2026-08-18T21:00:15.648039Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001714/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001714/DRAFT","etag":"feca5e62db072045d4e20ca44881f3f2c8993a8132c4b244a18c7871771d7ab3","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV1 Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-1) domain and regions (UniProtKB) dataset contains Severe acute respiratory syndrome-related coronavirus [taxid:694009] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome-related coronavirus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_domains_uniprotkb.csv","filename":"sarscov1_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov1_protein_domains_uniprotkb.stat.csv","filename":"sarscov1_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":438,"last_update":"2026-08-18T21:00:18.699281Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001715/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001715/DRAFT","etag":"28459d5f2d57e748e3663b560662b3952a9827f9c6b32cdd668ed7ef5e1638ad","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV2 Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) domain and regions citations (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_domains_uniprotkb.csv","filename":"sarscov2_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_citations_domains_uniprotkb.stat.csv","filename":"sarscov2_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":523,"last_update":"2026-08-18T21:00:21.751806Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001716/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001716/DRAFT","etag":"91f288a161be8849693dd9f5e81f73a6464e528d180ad73365970f85cfae0aab","spec_version":"1.3.0","provenance_domain":{"name":"SARS-CoV2 Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) domain and regions (UniProtKB) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Severe acute respiratory syndrome coronavirus 2","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_domains_uniprotkb.csv","filename":"sarscov2_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_domains_uniprotkb.stat.csv","filename":"sarscov2_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":447,"last_update":"2026-08-18T21:00:24.806997Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001717/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001717/DRAFT","etag":"3c0c7e1c3f1991334ab5c3b4b4ca11013b020165cae3e139f8d58d5e4ba50f23","spec_version":"1.3.0","provenance_domain":{"name":"Yeast Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast domain and regions citations (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_domains_uniprotkb.csv","filename":"yeast_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_citations_domains_uniprotkb.stat.csv","filename":"yeast_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":457,"last_update":"2026-08-18T21:00:27.856759Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001718/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001718/DRAFT","etag":"867e712f267d786ed4889f8089512b2b5888b6039d99439e7ede1bf73fbdfb64","spec_version":"1.3.0","provenance_domain":{"name":"Yeast Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast domain and regions (UniProtKB) dataset contains Saccharomyces cerevisiae S288C [taxid:559292] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_domains_uniprotkb.csv","filename":"yeast_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_domains_uniprotkb.stat.csv","filename":"yeast_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":381,"last_update":"2026-08-18T21:00:30.913695Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001719/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001719/DRAFT","etag":"a834c606a70888080c75a6a1ff2523056f1e29460ba258d457670d745c4ef7b3","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Domains and Regions Citations (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish domain and regions citations (UniProtKB) dataset contains Danio rerio [taxid:7955] publication information for UniProtKB canonical protein domains, motifs and DNA binding regions provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions Citations","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding","citations"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the PMID from the domain, motif or nucleotide binding annotation triples then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_domains_uniprotkb.csv","filename":"zebrafish_protein_citations_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_citations_domains_uniprotkb.stat.csv","filename":"zebrafish_protein_citations_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":437,"last_update":"2026-08-18T21:00:33.966572Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001720/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001720/DRAFT","etag":"9dc5afd27ce3248a228560b41f74a11e9021a2d12b4d65d2998f5d5a2067f7d3","spec_version":"1.3.0","provenance_domain":{"name":"Zebrafish Domains and Regions (UniProtKB)","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish domain and regions (UniProtKB) dataset contains Danio rerio [taxid:7955] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Domains and Regions","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"description_domain":{"keywords":["domains","motifs","regions","DNA binding"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.","prerequisite":[],"output_list":[]}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_domains_uniprotkb.csv","filename":"zebrafish_protein_domains_uniprotkb.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_domains_uniprotkb.stat.csv","filename":"zebrafish_protein_domains_uniprotkb.stat.csv"}}],"input_subdomain":[]},"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":361,"last_update":"2026-08-18T21:00:37.016166Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001721/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001721/DRAFT","etag":"02c145a359117d593ab885a72cb54f3cddf785306942905e24993adc8a962faa","spec_version":"1.3.0","provenance_domain":{"name":"Glycan Xref Extended PDB","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","contribution":["createdBy"],"email":"jeetvora@gwu.edu"},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Nathan Edwards","affiliation":"Georgetown University","contribution":["contributedBy"],"email":"nje5@georgetown.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The dataset provides cross-references to extended PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tag"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_name":"species","category_value":"Saccharomyces cerevisiae"},{"category_name":"species","category_value":"Drosophila melanogaster"},{"category_name":"species","category_value":"Homo sapiens"},{"category_name":"species","category_value":"Mus musculus"},{"category_name":"species","category_value":"Sus scrofa domesticus"},{"category_name":"species","category_value":"Rattus norvegicus"},{"category_name":"species","category_value":"Rattus"},{"category_name":"species","category_value":"Severe acute respiratory syndrome coronavirus 2"},{"category_name":"species","category_value":"Sus scrofa"},{"category_name":"species","category_value":"Dictyostelium discoideum"}]}}],"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","version":"","step_number":1,"input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[{"step":"","param":"","value":""}],"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_pdb_extended.csv","filename":"glycan_xref_pdb_extended.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_xref_pdb_extended.stat.csv","filename":"glycan_xref_pdb_extended.stat.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":391,"last_update":"2026-08-18T21:32:02.959884Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001722/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001722/DRAFT","spec_version":"1.3.0","etag":"431f9668691bac327b108fe4deaa3b8c3e4fdc697d16649851480bfb30206e97","provenance_domain":{"name":"Arabidopsis Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Arabidopsis Gene Groups dataset contains Arabidopsis thaliana [taxid:3702] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_gene_groups.csv","filename":"arabidopsis_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/arabidopsis_protein_gene_groups.stat.csv","filename":"arabidopsis_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Arabidopsis thaliana","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":905,"last_update":"2026-08-24T10:09:08.578561Z","access_count":0},{"object_id":"https://biocomputeobject.org/GLY_001723/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001723/DRAFT","spec_version":"1.3.0","etag":"b4692232dc764559eb1a09a6f3addd67bf39ecb236fa06452012ff73d44cf9a9","provenance_domain":{"name":"Bovine Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Bovine Gene Groups dataset contains Bos taurus [taxid:9913] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_gene_groups.csv","filename":"bovine_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/bovine_protein_gene_groups.stat.csv","filename":"bovine_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Bos taurus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":887,"last_update":"2026-08-24T10:09:11.627367Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001724/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001724/DRAFT","spec_version":"1.3.0","etag":"09de0b4f607a3c97e038e49b9720f1abe1506545ab43158b6715eaaddd0a91af","provenance_domain":{"name":"Chicken Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Chicken Gene Groups dataset contains Gallus gallus [taxid:9031] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_gene_groups.csv","filename":"chicken_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/chicken_protein_gene_groups.stat.csv","filename":"chicken_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Gallus gallus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":891,"last_update":"2026-08-24T10:09:14.677773Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001725/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001725/DRAFT","spec_version":"1.3.0","etag":"cfa5b7153a7bb5b98aff99ad39977cdf80e9b9303e00e56fd7a410a3849975e9","provenance_domain":{"name":"Dicty Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Dicty Gene Groups dataset contains Dictyostelium discoideum [taxid:44689] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_gene_groups.csv","filename":"dicty_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/dicty_protein_gene_groups.stat.csv","filename":"dicty_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Dictyostelium discoideum","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":903,"last_update":"2026-08-24T10:09:17.726092Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001726/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001726/DRAFT","spec_version":"1.3.0","etag":"984b061f5230ba9e4f9e380e811038e61f74840bd139576f2541882fa9963a6a","provenance_domain":{"name":"Fruitfly Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Fruitfly Gene Groups dataset contains Drosophila melanogaster [taxid:7227] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_gene_groups.csv","filename":"fruitfly_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_gene_groups.stat.csv","filename":"fruitfly_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Drosophila melanogaster","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":905,"last_update":"2026-08-24T10:09:20.773242Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001727/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001727/DRAFT","spec_version":"1.3.0","etag":"95fa44f1a838531e9aeaa8dd10445061c95093860dc695f63a77b2b852998cae","provenance_domain":{"name":"Hamster Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Hamster Gene Groups dataset contains Cricetulus griseus [taxid:10029]  UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_gene_groups.csv","filename":"hamster_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hamster_protein_gene_groups.stat.csv","filename":"hamster_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Cricetulus griseus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":900,"last_update":"2026-08-24T10:09:23.821490Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001728/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001728/DRAFT","spec_version":"1.3.0","etag":"6ed6487b0a52831834702af0070ceedba149c101511fca684d03bd878c41df0f","provenance_domain":{"name":"Human Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","modified":"2026-08-24T10:14:29.269Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Human Gene Groups dataset contains Homo sapiens [taxid:9606] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. The 'GlycoGenes' category also contain all glycan-related genes from the publication from UGA [PMID:18411279] which include glycosylhydrolases, glycosyltransferases, carbohydrate-binding modules and carbohydrate esterases, as defined by CAZy, Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like glycolipid-related, GAG-related, etc. There is also a gene group category for reviewed SwissProt proteins identified as immunoglobins in UniProtKB database by the keyword immunoglobin (Immunoglobulin [KW-1280]). If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, CAZy, and cite PMID:18411279."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, Glycan-modifying enzymes, and all genes in the publication input file. For the publication input file, the script maps the gene ids and gene names from the source file to UniProtKB canonical accession."}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_gene_groups.csv","filename":"human_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/human_protein_gene_groups.stat.csv","filename":"human_protein_gene_groups.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1569,"last_update":"2026-08-24T10:14:29.269083Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001729/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001729/DRAFT","spec_version":"1.3.0","etag":"d84fedc4c8bc6c28419bf18a292aa5b8fc300eb71693e31c4f3a2e1de1b5b971","provenance_domain":{"name":"Mouse Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Mouse Gene Groups dataset contains Mus musculus [taxid:10090] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. The 'GlycoGenes' category also contain all glycan-related genes retrieved from stem cell analysis using qRT-PCR [PMID:18411279], which include glycosylhydrolases, glycosyltransferases, carbohydrate-binding modules and carbohydrate esterases, as defined by CAZy, Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like glycolipid-related, GAG-related, etc. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, CAZy, and cite PMID:18411279."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, Glycan-modifying enzymes, and all genes in the publication input file. For the publication input file, the script maps the gene ids and gene names from the source file to UniProtKB canonical accession.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_gene_groups.csv","filename":"mouse_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_gene_groups.stat.csv","filename":"mouse_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":1385,"last_update":"2026-08-24T10:09:29.917946Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001730/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001730/DRAFT","spec_version":"1.3.0","etag":"cdd3bbb9a97e608c229daa055c1a5788f6aa56c8c7bfea078ba166544e63962a","provenance_domain":{"name":"Pig Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Pig Gene Groups dataset contains Sus scrofa [taxid:9823] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_gene_groups.csv","filename":"pig_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/pig_protein_gene_groups.stat.csv","filename":"pig_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Sus scrofa","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":883,"last_update":"2026-08-24T10:09:32.966491Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001731/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001731/DRAFT","spec_version":"1.3.0","etag":"a3af09b42026bcc036cb78473fb4be0ebd7038e33e1104f8406c088743667fb7","provenance_domain":{"name":"Rat Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Rat Gene Groups dataset contains Rattus norvegicus [taxid:10116] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_gene_groups.csv","filename":"rat_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/rat_protein_gene_groups.stat.csv","filename":"rat_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":893,"last_update":"2026-08-24T10:09:36.016918Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001732/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001732/DRAFT","spec_version":"1.3.0","etag":"f5c50504f39789a1860635cad99bd5c23f4697e944a3675cfecdb13165781a7e","provenance_domain":{"name":"Yeast Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Yeast Gene Groups dataset contains Saccharomyces cerevisiae S288C [taxid:559292] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_gene_groups.csv","filename":"yeast_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/yeast_protein_gene_groups.stat.csv","filename":"yeast_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Saccharomyces cerevisiae S288C","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":912,"last_update":"2026-08-24T10:09:39.066363Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001733/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001733/DRAFT","spec_version":"1.3.0","etag":"7e496296756ddb666d39cd94b2325eecc8700e1c6524fb113ac2ead826dff748","provenance_domain":{"name":"Zebrafish Gene Groups","version":"v-x.x.x","license":"\"https://creativecommons.org/licenses/by/4.0/\"","created":"","modified":"","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"],"orcid":""},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The Zebrafish Gene Groups dataset contains Danio rerio [taxid:7955] UniProtKB accessions that have been identified as potential proteins of interest for our users. Proteins are categorized into gene groups to enable identification and the 'Protein of Interest' filters on the protein list page of the GlyGen portal. The subcategories include all proteins in GlyGen defined as 'Glycosylhydrolases', 'Glycosyltransferases', or 'Glycan-modifying enzymes' by CAZy, and/or its enzyme classification in UniProtKB. The parent category 'GlycoGenes' encompasses the subcategories 'Glycosylhydrolases', 'Glycosyltransferases', and 'Glycan-modifying enzymes'. If you use this dataset, please provide proper attribution to UniProtKB, GlyGen, and CAZy."],"description_domain":{"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"input_list":[],"description":"The script extracts proteins of interest from the input datasets, maps them to the canonical UniProtKB canonical protein, and adds the gene_group categories of each protein. Added gene groups include the parent category GlycoGene, which contains the subcategories Glycosyltransferases, Glycosylhydrolases, and Glycan-modifying enzymes.","prerequisite":[],"output_list":[]}],"keywords":["Gene groups","GlycoGenes","Glycosyltransferases","Glycosylhydrolases","Glycan-modifying enzymes"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_gene_groups.csv","filename":"zebrafish_protein_gene_groups.csv"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/zebrafish_protein_gene_groups.stat.csv","filename":"zebrafish_protein_gene_groups.stat.csv"}}],"input_subdomain":[]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py","filename":"make-protein-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Danio rerio","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Groups","category_name":"tag"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":891,"last_update":"2026-08-24T10:09:42.115208Z","access_count":1},{"object_id":"https://biocomputeobject.org/GLY_001734/DRAFT","contents":{"object_id":"https://biocomputeobject.org/GLY_001734/DRAFT","spec_version":"1.3.0","etag":"969d6ad1e479633538bdd50b35ec2e08d028967f3d1bfbbf1bb90c2cf1e9645f","provenance_domain":{"name":"GlyGen-CFDE Glycans and Glycoenzymes Submission","version":"v-x.x.x","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2026-08-25T11:56:48.117Z","contributors":[{"name":"Jeet Vora","affiliation":"The George Washington University","email":"jeetvora@gwu.edu","contribution":["createdBy"]},{"name":"Robel Kahsay","affiliation":"The George Washington University","contribution":["createdBy"],"email":"rykahsay@gwu.edu"},{"name":"Urnisha Bhuiyan","affiliation":"The George Washington University","contribution":["createdBy"],"email":"sbhuiyan28@email.gwu.edu"},{"name":"Kate Warner","affiliation":"The George Washington University","contribution":["createdBy"],"email":"k.warner1@gwu.edu"}]},"usability_domain":["The GlyGen-CFDE Glycans and Glycoenzymes Submission dataset contains Homo sapiens [taxid:9606] glycans and their glycan synthesizing enzymes identified in GlyGen. The dataset is formatted as a XMT file for gene sets, i.e. '.gmt', for submission to the CFDE Workbench Metadata & Processed Data Matrix. If you use this dataset please provide proper attribution to GlyGen and CFDE."],"description_domain":{"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"input_list":[],"description":"The script maps fully-defined glycans to their synthesizing enzymes gene names, and formats the dataset into a gmt (XMT) format."}],"keywords":["CFDE","GlyGen","Glycans","Glycosyltransferases","Glycohydrolases","Glycoenzymes","Enzymes","crossreferences"]},"parametric_domain":[{"value":""}],"io_domain":{"output_subdomain":[{"mediatype":"gmt","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glygen_glycan_synthesizing_enzymes.gmt","filename":"glygen_glycan_synthesizing_enzymes.gmt"}},{"mediatype":"csv","uri":{"uri":"https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glygen_glycan_synthesizing_enzymes.stat.csv","filename":"glygen_glycan_synthesizing_enzymes.stat.csv"}}]},"execution_domain":{"script":[{"uri":{"uri":"https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}],"script_driver":"manual","software_prerequisites":[{"name":"Python","version":"2.7.5","uri":{"uri":"https://www.python.org/download/releases/2.7.5/"}}],"external_data_endpoints":[],"environment_variables":{}},"extension_domain":[{"extension_schema":"https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json","dataset_extension":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyGen-CFDE Glycans and Glycoenzymes","category_name":"tag"},{"category_value":"gmt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]}}],"error_domain":{}},"prefix":"GLY","owner":"k.warner1","authorized_users":null,"state":"DRAFT","score":458,"last_update":"2026-08-25T11:56:48.117695Z","access_count":1}]